© 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. 15898
    Prev
    Next
    INDEX
    Explanations

    code block beginnings

    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
     aislado
    -1.30
     húmedo
    -1.24
    -
    -1.17
     outcrops
    -1.14
    '
    -1.13
    ӏ
    -1.10
     auxquelles
    -1.08
     aéreo
    -1.08
     复
    -1.08
     censored
    -1.07
    POSITIVE LOGITS
     not
    1.26
     آمریک
    1.25
     می‌ده
    1.11
    卉
    1.10
     trabajo
    1.10
     in
    1.09
     if
    1.05
     have
    1.02
    ども
    1.00
     です
    0.98
    Activations Density 0.017%

    No Known Activations