© 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. 61715
    Prev
    Next
    INDEX
    Explanations

    programming data structures and logic

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

    commissioned, enchanted, request, assistance

    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
    дов
    0.52
    новых
    0.50
    (^^
    0.48
     под
    0.46
    녠
    0.46
    zcz
    0.45
    дь
    0.45
    nije
    0.45
    рий
    0.44
     է
    0.44
    POSITIVE LOGITS
    Array
    0.48
    Assign
    0.47
    Animal
    0.46
    Animation
    0.45
    𒋫
    0.44
    Ass
    0.43
    ০০
    0.43
     सीई
    0.43
    Animator
    0.43
    Iterable
    0.43
    Activations Density 0.000%

    No Known Activations