© 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. 65072
    Prev
    Next
    INDEX
    Explanations

    valve components

    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
    n
    -2.64
    an
    -2.59
    [
    -2.42
     großes
    -2.36
    t
    -2.28
    en
    -2.28
    r
    -2.19
     \
    -2.13
    for
    -2.08
    ஂ
    -2.08
    POSITIVE LOGITS
    薷
    2.63
    嫆
    2.52
     navegador
    2.47
    ⑉
    2.38
    鎰
    2.38
     coloriage
    2.34
     kosme
    2.31
    ЕМ
    2.30
     ideen
    2.30
     keram
    2.28
    Activations Density 0.015%

    No Known Activations