© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12561
    Prev
    Next
    INDEX
    Explanations

    names ending in anga

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

    This neuron detects the character sequence “anga” (as found in place names or demonyms).

    oai_token-act-pair · o4-miniTriggered 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
    the
    -3.28
    The
    -3.25
    A
    -3.16
    h
    -3.03
    E
    -2.95
    "
    -2.95
    l
    -2.94
    '
    -2.86
    er
    -2.75
    We
    -2.72
    POSITIVE LOGITS
    anga
    2.84
     outros
    2.69
    鸵
    2.34
    ANGA
    2.30
     poignant
    2.25
    家主
    2.16
    鄠
    2.16
    让她
    2.16
     Generally
    2.14
    ⩤
    2.14
    Activations Density 0.009%

    No Known Activations