© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107052
    Prev
    Next
    INDEX
    Explanations

    figure and table references

    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
     Şi
    -0.84
    olkien
    -0.84
     pudieron
    -0.82
    يست
    -0.81
    ე
    -0.81
     搭配
    -0.81
     Christo
    -0.80
    ⒍
    -0.80
    ナリ
    -0.79
    Şi
    -0.79
    POSITIVE LOGITS
    <b>
    0.98
    <strong>
    0.84
    )">
    0.84
     OMITTED
    0.82
     illustrated
    0.81
    庁
    0.80
    cerea
    0.79
     somewhere
    0.77
     ještě
    0.77
    utom
    0.76
    Activations Density 0.024%

    No Known Activations