© 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. 15068
    Prev
    Next
    INDEX
    Explanations

    military establishment, console versions, Android app

    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
     for
    -1.28
     causing
    -1.23
     when
    -1.21
     on
    -1.15
     at
    -1.11
     enticing
    -1.09
     kematian
    -1.07
     with
    -1.05
     in
    -1.02
     around
    -1.02
    POSITIVE LOGITS
     verdaderas
    1.09
     unimagin
    1.07
     oublier
    1.03
     terse
    1.02
     tranquil
    1.01
     occuper
    1.01
     interrom
    1.00
     malgré
    0.99
     quintessential
    0.99
     ferocious
    0.98
    Activations Density 0.286%

    No Known Activations