© 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. 90578
    Prev
    Next
    INDEX
    Explanations

    heat treatment and transfer

    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
    m
    -2.89
    ed
    -2.77
    li
    -2.64
    the
    -2.61
    ’
    -2.45
    ፨
    -2.42
    見た
    -2.31
    刧
    -2.31
    ”
    -2.28
    .")
    -2.22
    POSITIVE LOGITS
    咵
    2.92
    是非常
    2.84
    ޗ
    2.77
    不论
    2.64
     стоковые
    2.56
     flere
    2.53
     continúa
    2.48
    genodigd
    2.45
     unſ
    2.36
    pulseira
    2.36
    Activations Density 0.016%

    No Known Activations