© 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. 34-GEMMASCOPE-RES-131K
    7. 108833
    Prev
    Next
    INDEX
    Explanations

    film actors

    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_34/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
    kle
    -0.79
    раб
    -0.75
     음
    -0.75
    kimi
    -0.74
    cepción
    -0.74
     langer
    -0.73
    velse
    -0.73
    Ć
    -0.73
     UNIT
    -0.73
    ampled
    -0.72
    POSITIVE LOGITS
     film
    0.78
     filmmakers
    0.76
     לב
    0.71
    少
    0.71
     acting
    0.71
     films
    0.71
     actors
    0.71
    gains
    0.70
     artístico
    0.70
    ~/
    0.70
    Activations Density 0.080%

    No Known Activations