© 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. 79217
    Prev
    Next
    INDEX
    Explanations

    style, houses, case, villages

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

    travel planners

    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
    ala
    0.49
    ne
    0.45
    ela
    0.45
    e
    0.45
    var
    0.42
     triumph
    0.42
    ли
    0.42
    ette
    0.41
    ard
    0.41
    الص
    0.41
    POSITIVE LOGITS
     nombreuses
    0.54
     harass
    0.46
     indoct
    0.46
    爌
    0.46
     harassment
    0.45
    ่ม
    0.45
     Präsident
    0.44
    霾
    0.44
     incênd
    0.44
     Hobbit
    0.44
    Activations Density 0.001%

    No Known Activations