© 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. 76801
    Prev
    Next
    INDEX
    Explanations

    damage, paints, fund, first, flying

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

    sales director, general RDA, tribal ship

    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
     পরিবর্ত
    0.50
    baixo
    0.48
     言っ
    0.48
    conte
    0.47
     장
    0.44
     milites
    0.43
     聞い
    0.43
     દ્વા
    0.43
     この
    0.42
     어느
    0.42
    POSITIVE LOGITS
     fight
    0.48
     topographic
    0.45
     naturalist
    0.45
     topological
    0.45
     sej
    0.44
     hemisphere
    0.44
     natuurlijk
    0.43
    /
    0.43
     detriment
    0.43
     transgenic
    0.42
    Activations Density 0.000%

    No Known Activations