© 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. 34153
    Prev
    Next
    INDEX
    Explanations

    if statements

    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
     parfüm
    -2.28
    푉
    -2.19
     kabát
    -2.14
    archiwizowane
    -2.06
     cinto
    -2.05
    damen
    -2.05
     וכן
    -2.05
     semelh
    -2.02
     dámské
    -2.02
     dáms
    -2.00
    POSITIVE LOGITS
     (
    2.83
    !
    2.28
     in
    2.16
    2.08
    ’
    1.97
    (
    1.78
     not
    1.77
    大多
    1.77
    u
    1.74
    “
    1.74
    Activations Density 0.015%
    No Known Activations