© 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. 10-GEMMASCOPE-RES-131K
    7. 72445
    Prev
    Next
    INDEX
    Explanations

    Marine Corps

    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
    ”
    -1.79
    “
    -1.63
    *
    -1.63
    
    -1.61
    )
    -1.60
     ALLA
    -1.52
    
    -1.51
    sandalia
    -1.51
    х
    -1.48
    ون
    -1.46
    POSITIVE LOGITS
     where
    1.59
    诘
    1.57
     would
    1.44
     will
    1.43
    ）」
    1.41
    b
    1.40
    ATIONS
    1.38
    鼈
    1.38
    henswürdigkeiten
    1.38
    replyreport
    1.34
    Activations Density 0.010%

    No Known Activations