© 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. 182174
    Prev
    Next
    INDEX
    Explanations

    myself . | subject is | great review | never write

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

    numbers and records

    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
     Enseñ
    0.53
     activación
    0.50
     aulas
    0.49
     vitaminas
    0.49
    ેશન
    0.46
     arranc
    0.46
    酆
    0.46
     sacar
    0.46
     의해
    0.45
     automático
    0.45
    POSITIVE LOGITS
    u
    0.68
    k
    0.57
    time
    0.53
    EE
    0.53
     Colonel
    0.53
    recover
    0.52
    y
    0.51
    lime
    0.50
     wonderful
    0.49
    Mirror
    0.49
    Activations Density 0.000%

    No Known Activations