© 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. 23607
    Prev
    Next
    INDEX
    Explanations

    specific scenarios

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

    here to help

    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
     définie
    0.46
    ଶ
    0.46
    m
    0.45
     exceptionnelle
    0.45
     отсутствует
    0.45
    व
    0.44
    TO
    0.44
    iglia
    0.43
    Sh
    0.43
     обраща
    0.43
    POSITIVE LOGITS
    ഘാ
    0.47
     alliances
    0.47
     Existen
    0.46
     worldRank
    0.44
     especie
    0.43
    commonByteArray
    0.42
    影
    0.42
     जीत
    0.41
     প্রার্থী
    0.41
     Salaries
    0.41
    Activations Density 0.000%

    No Known Activations