© 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. 90732
    Prev
    Next
    INDEX
    Explanations

    programming and technical questions

    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
    <blockquote>
    -1.78
    LikeLike
    -0.97
    <h4>
    -0.82
    <h3>
    -0.81
     ample
    -0.77
    Schedulers
    -0.77
     различ
    -0.76
    آباد
    -0.76
     NSMutable
    -0.75
    plication
    -0.75
    POSITIVE LOGITS
    /#
    1.00
    ">—
    0.93
    )&&(
    0.89
    )>=
    0.84
    )==
    0.84
     narzęd
    0.83
     tornillo
    0.83
     niitä
    0.82
    ')")
    0.82
     zostać
    0.82
    Activations Density 0.097%

    No Known Activations