© 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. 30262
    Prev
    Next
    INDEX
    Explanations

    customize your, desire to, site map

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

    software dependencies

    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
    ట్ల
    0.52
     wildest
    0.49
     zoveel
    0.47
     kiddos
    0.47
     cardamom
    0.47
     sweetheart
    0.46
     spezi
    0.45
    倡
    0.45
     zucch
    0.45
     kidnap
    0.45
    POSITIVE LOGITS
    AC
    0.46
     때
    0.46
    os
    0.44
     때는
    0.43
     décrite
    0.43
    Threshold
    0.41
    IR
    0.40
    IN
    0.40
    When
    0.39
     When
    0.39
    Activations Density 0.000%

    No Known Activations