© 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. 111771
    Prev
    Next
    INDEX
    Explanations

    etc. and similar listing markers

    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
    
    -2.25
     itſelf
    -2.03
     caufe
    -2.02
    霂
    -1.98
     niedersachsen
    -1.89
     authenti
    -1.89
    蕺
    -1.88
    )：
    -1.88
    櫺
    -1.88
    焄
    -1.87
    POSITIVE LOGITS
    ed
    2.27
     to
    2.17
    of
    2.16
    楽しみに
    2.11
    (
    2.09
     —
    2.06
    )
    2.05
     škola
    1.95
     in
    1.94
    峥
    1.93
    Activations Density 0.001%

    No Known Activations