© 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. 169312
    Prev
    Next
    INDEX
    Explanations

    header layout and design

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

    HTML header tags

    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
     skull
    0.52
     tilt
    0.46
     株
    0.45
     retardation
    0.44
     голове
    0.44
     заги
    0.43
     やつ
    0.42
     goatee
    0.41
     goblet
    0.41
     slouch
    0.40
    POSITIVE LOGITS
     Economía
    0.54
     economía
    0.52
    טו
    0.51
    عيد
    0.51
    يلة
    0.51
    бла
    0.50
     privados
    0.49
    ز
    0.49
     interacción
    0.48
     convivencia
    0.48
    Activations Density 0.001%

    No Known Activations