© 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. 10328
    Prev
    Next
    INDEX
    Explanations

    accessories and components

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

    accessories, tools, and sports equipment

    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
     http
    0.47
    %,
    0.44
     (
    0.42
     Gallup
    0.41
     www
    0.40
    http
    0.40
     parliamentary
    0.40
     publishes
    0.40
     तथा
    0.39
    ²
    0.39
    POSITIVE LOGITS
    温馨
    0.43
    衹
    0.42
    larghezza
    0.41
    טורק
    0.40
    煅
    0.40
    শিল্প
    0.39
    Telefono
    0.39
     brinqu
    0.39
     подар
    0.38
    Projectile
    0.38
    Activations Density 0.001%

    No Known Activations