© 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. 95701
    Prev
    Next
    INDEX
    Explanations

    travel and distance

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

    software development and technical concepts

    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
    готовить
    0.48
    輥
    0.48
    อาหาร
    0.46
    നീ
    0.46
     किसानों
    0.45
     умень
    0.45
     Watershed
    0.45
     увеличить
    0.44
    ଯ
    0.44
     बैंकों
    0.44
    POSITIVE LOGITS
     on
    0.50
     perdu
    0.45
     nid
    0.45
     baggage
    0.44
     consola
    0.42
     solcher
    0.42
     from
    0.41
    XXX
    0.41
     avete
    0.40
    (/
    0.40
    Activations Density 0.003%

    No Known Activations