© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72896
    Prev
    Next
    INDEX
    Explanations

    words beginning with Am

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron strongly activates on the standalone token “Am” (as in journal or organization abbreviations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the capitalized subword prefix "Am" at the start of names or abbreviations.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the token "Am" when it appears as part of a proper noun, abbreviation, or author name in technical or formal text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cielos
    -2.78
     hectáreas
    -2.70
    ]
    -2.69
    以便
    -2.64
    鹮
    -2.63
     który
    -2.59
    啬
    -2.59
    􏿿
    -2.56
    ſſel
    -2.53
    驺
    -2.48
    POSITIVE LOGITS
     Это
    2.95
     They
    2.80
    {
    2.75
     According
    2.70
     Interestingly
    2.69
    Since
    2.56
     Для
    2.52
     Despite
    2.47
     Unfortunately
    2.45
    спомина
    2.42
    Activations Density 0.005%

    No Known Activations