© 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. 44343
    Prev
    Next
    INDEX
    Explanations

    casualty occurrences

    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
     které
    -2.53
    蟊
    -2.33
     eminently
    -2.31
     tropicales
    -2.19
     europeo
    -2.11
    のは
    -2.09
    ULTURAL
    -2.06
     или
    -2.03
     blancas
    -2.02
     WHICH
    -2.00
    POSITIVE LOGITS
    s
    2.42
    ↵
    2.42
    \\
    2.36
    }
    2.36
    _{
    2.27
     
    2.20
    i
    2.11
    舠
    2.11
    觧
    2.11
    牁
    2.05
    Activations Density 0.005%

    No Known Activations