© 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. 187405
    Prev
    Next
    INDEX
    Explanations

    religious themes and latino culture

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

    prices, control, growth

    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
    wenn
    0.48
     Greatest
    0.47
     וש
    0.47
     wharf
    0.45
     przechowy
    0.43
    㡱
    0.43
    amh
    0.43
     marina
    0.42
     Systems
    0.42
     strictly
    0.41
    POSITIVE LOGITS
    цев
    0.48
    قل
    0.47
    г
    0.46
    icas
    0.45
    𝚗
    0.45
     payoffs
    0.44
     delanter
    0.44
     다음
    0.44
    hereinafter
    0.44
    리즈
    0.43
    Activations Density 0.000%

    No Known Activations