© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 38603
    Prev
    Next
    INDEX
    Explanations

    APPENDIX, Internal, Documentation, November

    np_acts-logits-general · gemini-2.5-flash-lite

    definitions and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     чита
    0.50
    简单的
    0.49
     читать
    0.48
    简单
    0.47
    簡單
    0.46
     чтения
    0.46
     potete
    0.45
     這
    0.44
     beatae
    0.44
     የ
    0.44
    POSITIVE LOGITS
     Symph
    0.46
     mortars
    0.46
     Chairman
    0.42
     Personnel
    0.42
     ৩২
    0.42
    рих
    0.41
     Ber
    0.41
    abri
    0.41
     airlift
    0.40
     aircraft
    0.40
    Activations Density 0.000%

    No Known Activations