© 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. 14398
    Prev
    Next
    INDEX
    Explanations

    whether to define

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

    historical events

    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
    v
    0.60
    0.54
    ↵↵↵
    0.53
    r
    0.53
    L
    0.53
    -
    0.50
    reate
    0.50
    more
    0.49
    create
    0.48
    H
    0.48
    POSITIVE LOGITS
    დომ
    0.65
     μα
    0.59
    𒍪
    0.57
     মিনিটে
    0.56
     συνα
    0.56
    ﺏ
    0.55
     ആക്രമ
    0.55
    𒅎
    0.55
     값을
    0.54
    괵
    0.52
    Activations Density 0.000%

    No Known Activations