© 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. 127293
    Prev
    Next
    INDEX
    Explanations

    metered, methanol, mebumalum, metabolites, meandering

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

    the prefix "me" at the beginning of words.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ]
    -4.22
    t
    -3.33
    」
    -3.27
    {
    -3.19
    to
    -3.11
    b
    -3.08
    an
    -2.92
    –
    -2.89
    ner
    -2.84
    »
    -2.80
    POSITIVE LOGITS
    ญี่ป
    3.03
    棡
    2.86
     Chriſt
    2.73
    臜
    2.73
    屺
    2.66
     parachoque
    2.66
    
    2.66
    谪
    2.59
    
    2.56
    vantaged
    2.48
    Activations Density 0.036%

    No Known Activations