© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63087
    Prev
    Next
    INDEX
    Explanations

    bring forward, take time

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

    Early Spanish

    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
     order
    0.47
    É
    0.46
    Protect
    0.45
     IDENTITY
    0.44
     FILM
    0.44
    Ě
    0.43
    ST
    0.43
     EQUIPMENT
    0.43
     nodal
    0.42
    Τ
    0.42
    POSITIVE LOGITS
     یافته
    0.46
     LongNumber
    0.46
     بين
    0.45
     خالد
    0.44
     novedad
    0.43
     exd
    0.43
    ين
    0.43
     experimento
    0.42
     находи
    0.42
    dDays
    0.42
    Activations Density 0.000%

    No Known Activations