© 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. 72617
    Prev
    Next
    INDEX
    Explanations

    set of X, way of Y

    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
     also
    -1.26
    œuvres
    -1.23
    も
    -1.16
    ,
    -1.15
     například
    -1.13
    OTHER
    -1.11
     innych
    -1.09
     других
    -1.05
    肩膀
    -1.04
     from
    -1.03
    POSITIVE LOGITS
    attare
    1.10
    🪸
    1.08
    ēja
    1.07
    WebElementEntity
    1.04
    的照片
    1.04
    prech
    1.03
    dată
    1.02
     considérons
    1.01
     ventures
    1.00
     Occidente
    1.00
    Activations Density 0.079%

    No Known Activations