© 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. 73008
    Prev
    Next
    INDEX
    Explanations

    code identifiers, keywords, and punctuation

    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
    ถ้า
    -1.16
    INSEE
    -1.13
    Έ
    -1.08
    merken
    -1.08
    Iš
    -1.08
    باس
    -1.05
     terminée
    -1.02
    مرا
    -1.02
    次の
    -1.00
     lavable
    -1.00
    POSITIVE LOGITS
     in
    1.10
     می‌گوید
    1.02
    la
    0.98
    ,
    0.98
     (
    0.94
    but
    0.93
    wa
    0.92
     to
    0.91
     ameryka
    0.89
    /
    0.87
    Activations Density 0.045%

    No Known Activations