© 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. 26172
    Prev
    Next
    INDEX
    Explanations

    code block 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
     any
    -1.22
     not
    -1.16
     for
    -1.08
    z
    -1.07
     with
    -1.05
     from
    -1.02
     if
    -1.02
     continue
    -1.02
     should
    -1.01
     may
    -0.96
    POSITIVE LOGITS
     huéspedes
    1.23
     rette
    1.21
     mortos
    1.17
     illustre
    1.16
     boden
    1.16
    sommer
    1.16
    ਫ਼
    1.16
     emprunt
    1.16
     estampado
    1.16
     peluche
    1.16
    Activations Density 0.023%

    No Known Activations