© 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. 16279
    Prev
    Next
    INDEX
    Explanations

    database connection strings

    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
     or
    -1.20
     for
    -1.17
     only
    -1.08
     when
    -1.07
     by
    -1.07
     at
    -1.03
     all
    -1.02
     people
    -1.02
     any
    -1.00
     on
    -0.98
    POSITIVE LOGITS
     interrom
    1.18
    閖
    1.13
     corriger
    1.09
     MAJOR
    1.08
    けっこう
    1.04
     terminer
    1.03
     gän
    1.03
     diminuer
    1.02
     küche
    1.02
     armazen
    1.02
    Activations Density 0.010%

    No Known Activations