© 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. 38481
    Prev
    Next
    INDEX
    Explanations

    complementary biological concepts

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

    Dynamic Typing

    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
     geheel
    0.49
    accouchement
    0.47
     kracht
    0.42
    ട്ട
    0.41
     salarié
    0.41
    --;
    0.40
     bào
    0.40
     głów
    0.40
     randomNumber
    0.40
    LLO
    0.39
    POSITIVE LOGITS
    ref
    0.43
    compatible
    0.43
    molecular
    0.43
    complement
    0.42
    diff
    0.42
    bio
    0.42
    apos
    0.41
     Assert
    0.41
    dominated
    0.40
    斷
    0.40
    Activations Density 0.000%

    No Known Activations