© 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. 77801
    Prev
    Next
    INDEX
    Explanations

    authors, initials, and names

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

    initials and surnames

    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
    DataXYZ
    0.61
    etzung
    0.58
    ॠ
    0.58
    hitth
    0.58
    ৮
    0.55
    硚
    0.55
     इक्वेशन
    0.55
    ೪
    0.55
    EntityType
    0.54
    MiddleLine
    0.54
    POSITIVE LOGITS
    D
    0.70
    S
    0.65
    J
    0.64
     J
    0.61
     D
    0.61
    G
    0.61
    N
    0.60
    0.57
     i
    0.55
    M
    0.53
    Activations Density 0.000%

    No Known Activations