© 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. 99536
    Prev
    Next
    INDEX
    Explanations

    legal or technical terms followed by identifiers

    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
    envie
    -0.68
    Ngu
    -0.67
     Guts
    -0.66
    maxsize
    -0.66
    Cze
    -0.66
    Glas
    -0.63
    PAST
    -0.63
    ປ
    -0.63
     expla
    -0.62
    bowler
    -0.62
    POSITIVE LOGITS
    parentNode
    0.68
    蝶
    0.68
    zzo
    0.66
     Photon
    0.63
    ストリー
    0.63
    November
    0.61
    Ident
    0.61
    bea
    0.61
    dington
    0.61
    Jul
    0.60
    Activations Density 0.126%

    No Known Activations