© 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. 32360
    Prev
    Next
    INDEX
    Explanations

    free to, free software

    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
     Athenians
    -0.84
    Telefon
    -0.82
     thereafter
    -0.81
    Ingrédients
    -0.81
    EXACT
    -0.80
     EVER
    -0.80
    <blockquote>
    -0.79
    人類
    -0.75
    pantalones
    -0.75
     cement
    -0.75
    POSITIVE LOGITS
     free
    1.04
    free
    1.03
     feel
    0.95
     tell
    0.88
     told
    0.83
     let
    0.83
    ICKS
    0.82
     кӀ
    0.82
    >),
    0.81
     galloping
    0.79
    Activations Density 0.009%

    No Known Activations