© 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. 64935
    Prev
    Next
    INDEX
    Explanations

    internal class definitions

    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
     biela
    -1.77
    鱨
    -1.73
    蛱
    -1.71
     elevador
    -1.64
     histó
    -1.64
     akci
    -1.63
     Fácil
    -1.63
     aguj
    -1.61
     coronel
    -1.59
    podob
    -1.58
    POSITIVE LOGITS
    m
    2.22
    is
    2.03
    re
    2.02
    it
    1.93
    b
    1.85
    s
    1.81
    u
    1.81
    d
    1.78
    me
    1.77
    r
    1.75
    Activations Density 0.000%

    No Known Activations