© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 209135
    Prev
    Next
    INDEX
    Explanations

    blue curaçao

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

    reducing by eliminating

    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
    हा
    0.46
    плат
    0.44
    デア
    0.44
    publishing
    0.44
    GEO
    0.44
    期待
    0.43
    メル
    0.43
    ཊ
    0.43
    蜷
    0.43
    setting
    0.43
    POSITIVE LOGITS
     towards
    0.50
     eliminates
    0.48
     eliminar
    0.48
     southern
    0.47
     Alcohol
    0.47
     rescues
    0.47
     flanks
    0.47
     eliminate
    0.46
    acios
    0.46
     gusts
    0.46
    Activations Density 0.000%

    No Known Activations