© 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. 40024
    Prev
    Next
    INDEX
    Explanations

    decapitation, guillotine, headless, faceless

    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
    ar
    -2.67
    s
    -2.19
    ↵↵
    -2.11
    over
    -2.03
    The
    -2.00
     namun
    -2.00
    ⬯
    -1.95
    陞
    -1.88
    this
    -1.88
    se
    -1.88
    POSITIVE LOGITS
     seguimos
    2.08
    ’)
    2.06
    罴
    2.00
     hablamos
    1.83
     создания
    1.82
     profundamente
    1.81
    』『
    1.80
     parfüm
    1.80
    ’).
    1.80
     vivimos
    1.78
    Activations Density 0.007%

    No Known Activations