© 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. 12224
    Prev
    Next
    INDEX
    Explanations

    very first

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    镲
    -1.99
    ↵↵
    -1.88
     bénéficiaire
    -1.77
     ect
    -1.72
    <bos>
    -1.70
    .
    -1.63
    but
    -1.61
    猻
    -1.59
     $\&$
    -1.57
    ヒール
    -1.56
    POSITIVE LOGITS
    呦
    2.13
     After
    2.08
    傀
    1.98
     inspiradoras
    1.92
    除去
    1.90
     Probably
    1.90
     There
    1.90
    发布于
    1.89
    酩
    1.88
    PUESTA
    1.86
    Activations Density 0.004%

    No Known Activations