© 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. 10-GEMMASCOPE-RES-131K
    7. 14772
    Prev
    Next
    INDEX
    Explanations

    required by

    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
    {
    -3.80
    \
    -3.44
    A
    -3.33
    )
    -3.05
    O
    -2.98
    ."
    -2.92
    ?”
    -2.55
     在
    -2.52
    くちゃ
    -2.52
    q
    -2.50
    POSITIVE LOGITS
    鰾
    3.38
    勍
    3.03
    Donativos
    2.92
    唞
    2.88
     transparencia
    2.86
    哢
    2.73
    焄
    2.69
    趼
    2.66
    翾
    2.63
    ſelves
    2.59
    Activations Density 0.051%

    No Known Activations