© 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. 34-GEMMASCOPE-RES-131K
    7. 59163
    Prev
    Next
    INDEX
    Explanations

    prior to

    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_34/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
     and
    -2.22
     useAppContext
    -1.78
     but
    -1.63
    »;
    -1.56
    ❣
    -1.53
    🤌
    -1.49
    :),
    -1.49
     that
    -1.48
    wwwww
    -1.48
    wwwwwwww
    -1.48
    POSITIVE LOGITS
     erwäh
    1.88
     ständig
    1.76
     поскольку
    1.70
    訁
    1.67
    <blockquote>
    1.65
     verbre
    1.63
     the
    1.63
    since
    1.63
     The
    1.62
     It
    1.60
    Activations Density 0.117%

    No Known Activations