© 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. 15911
    Prev
    Next
    INDEX
    Explanations

    programming declarations

    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
     kabát
    -1.63
     Congrès
    -1.26
     kontro
    -1.22
     velg
    -1.21
     花朵
    -1.20
     páns
    -1.19
     berger
    -1.19
     blanches
    -1.18
     klient
    -1.17
     tém
    -1.16
    POSITIVE LOGITS
     it
    1.13
    La
    1.13
    with
    1.09
     for
    1.09
    n
    1.07
    L
    1.06
    r
    1.04
    Y
    1.03
    new
    1.03
    ;
    1.03
    Activations Density 0.010%

    No Known Activations