© 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. 81483
    Prev
    Next
    INDEX
    Explanations

    terms of service and website usage

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

    hand splitting

    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
     olives
    0.44
     buffered
    0.43
    ของ
    0.43
    DIN
    0.42
     assolutamente
    0.42
     grano
    0.42
    ⑪
    0.42
     actual
    0.41
    後半
    0.41
    Σ
    0.41
    POSITIVE LOGITS
    swift
    0.46
    équipement
    0.45
    sneak
    0.45
    fire
    0.44
    ét
    0.43
    actionMode
    0.43
    يران
    0.42
    changing
    0.42
    siege
    0.42
    écriture
    0.41
    Activations Density 0.000%

    No Known Activations