© 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. 34-GEMMASCOPE-RES-131K
    7. 93847
    Prev
    Next
    INDEX
    Explanations

    citation 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_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
    がありません
    -0.82
    putar
    -0.78
    Compile
    -0.75
    נו
    -0.75
    突
    -0.74
    kule
    -0.72
    ESTRA
    -0.71
    ("_
    -0.71
     Erstellung
    -0.71
    ном
    -0.71
    POSITIVE LOGITS
    αι
    0.84
    ходили
    0.82
    izioni
    0.74
     Requ
    0.71
    ￭
    0.70
     plaques
    0.68
     Oliva
    0.68
     memorize
    0.68
    ائم
    0.67
     Marken
    0.67
    Activations Density 0.029%

    No Known Activations