© 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. 78899
    Prev
    Next
    INDEX
    Explanations

    data class definitions

    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
    estimm
    -0.77
    anthe
    -0.73
    brushes
    -0.72
     thẻ
    -0.69
     honra
    -0.68
    ITUTION
    -0.68
     avanzada
    -0.66
    動く
    -0.66
     adaptarse
    -0.64
    marzo
    -0.63
    POSITIVE LOGITS
     ATK
    0.77
     strepto
    0.77
    Stein
    0.76
     explo
    0.72
    尺寸
    0.71
     Wanted
    0.70
     Strepto
    0.69
     стреми
    0.68
     Daten
    0.68
     Nike
    0.68
    Activations Density 0.050%

    No Known Activations