© 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. 34159
    Prev
    Next
    INDEX
    Explanations

    numbers and list delimiters

    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
    OffsetX
    -0.90
     up
    -0.82
     that
    -0.82
    Життєпис
    -0.79
    傚
    -0.77
    offsetof
    -0.75
     vagyok
    -0.75
     socket
    -0.75
     from
    -0.75
    ())->
    -0.74
    POSITIVE LOGITS
     sinter
    0.89
     pengar
    0.81
    idió
    0.79
     Ukraina
    0.79
     pregă
    0.79
     kênh
    0.78
     Toutes
    0.78
    רות
    0.78
     ngo
    0.77
     Maintenant
    0.76
    Activations Density 0.051%

    No Known Activations