© 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. 15894
    Prev
    Next
    INDEX
    Explanations

    academic publication identifiers

    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
    〜！
    -1.11
     also
    -1.00
     organizations
    -0.98
    marvin
    -0.96
    maxWidth
    -0.95
    〜。
    -0.95
     equipment
    -0.95
    bigr
    -0.94
     organizado
    -0.93
     like
    -0.93
    POSITIVE LOGITS
    Dile
    1.15
    है
    1.09
     günlük
    1.08
     этих
    1.07
    تهى
    1.04
     tieto
    0.99
    ஏ
    0.99
    Pairing
    0.99
    Pus
    0.99
    这些
    0.98
    Activations Density 0.002%

    No Known Activations