© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86379
    Prev
    Next
    INDEX
    Explanations

    network acronyms and 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_10/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
    that
    -2.48
     That
    -2.45
    焌
    -2.41
    
    -2.38
    缡
    -2.23
    祤
    -2.23
    椟
    -2.23
    
    -2.20
    呖
    -2.14
     ส์
    -2.11
    POSITIVE LOGITS
    (
    2.36
     prominently
    2.08
    “
    2.00
    ...
    1.87
    、
    1.85
     thier
    1.82
    』。
    1.82
    "—
    1.82
     jako
    1.81
    —
    1.75
    Activations Density 0.001%

    No Known Activations