© 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. 22-GEMMASCOPE-RES-131K
    7. 65051
    Prev
    Next
    INDEX
    Explanations

    whole or complete

    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_22/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
    Arbeits
    -0.92
    первых
    -0.87
     نداشته
    -0.85
    Voltar
    -0.85
     często
    -0.85
     eficaz
    -0.82
    zurück
    -0.82
    ƛ
    -0.81
     segera
    -0.81
    ánt
    -0.81
    POSITIVE LOGITS
     entire
    2.17
     whole
    1.90
     полноцен
    1.72
     full
    1.70
    本格
    1.41
    Entire
    1.41
     كامل
    1.41
     Entire
    1.31
     целый
    1.31
     broader
    1.29
    Activations Density 0.057%

    No Known Activations