© 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. 22-GEMMASCOPE-RES-131K
    7. 72062
    Prev
    Next
    INDEX
    Explanations

    stories and character relationships

    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_22/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
     parseFrom
    -1.12
    的说道
    -1.09
     during
    -1.08
    !
    -1.07
    andExpect
    -1.07
     району
    -1.07
    If
    -1.06
     рецепта
    -1.05
     if
    -1.05
     October
    -1.04
    POSITIVE LOGITS
    basically
    1.40
    $;
    1.32
    Specifically
    1.27
     laranja
    1.25
    essentially
    1.21
    specifically
    1.20
    canActivate
    1.17
     copos
    1.17
    sü
    1.15
     variados
    1.13
    Activations Density 0.015%

    No Known Activations