© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49562
    Prev
    Next
    INDEX
    Explanations

    date and time 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
    〰
    -1.00
    心裡
    -0.96
    Дмитрий
    -0.93
     snad
    -0.92
     poder
    -0.92
     τά
    -0.91
    帐户
    -0.91
     sangat
    -0.91
    Makan
    -0.90
    reszcie
    -0.90
    POSITIVE LOGITS
    Р
    0.96
    ция
    0.94
    MouseUp
    0.93
     divertida
    0.91
    :.
    0.91
    曾经
    0.90
     després
    0.89
    ラーメン
    0.88
    太多
    0.88
     Sacchar
    0.88
    Activations Density 0.046%

    No Known Activations