© 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. 33088
    Prev
    Next
    INDEX
    Explanations

    foreign language terms

    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
     to
    -1.63
    v
    -1.20
    z
    -1.16
    b
    -1.11
    m
    -1.09
    g
    -1.09
    w
    -1.07
    d
    -1.07
    h
    -1.04
    ch
    -1.03
    POSITIVE LOGITS
     sweter
    1.35
     llavero
    1.31
    čít
    1.21
     mojej
    1.17
     roues
    1.17
     pulsera
    1.16
    ρων
    1.14
     suéter
    1.14
     feveral
    1.13
     ennemis
    1.13
    Activations Density 0.110%

    No Known Activations