© 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. 155798
    Prev
    Next
    INDEX
    Explanations

    used as a reference

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

    describing actions, roles, or states

    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
    StartPreview
    0.51
    dateFormat
    0.47
    vať
    0.45
    保养
    0.45
    우
    0.43
    টাকে
    0.43
    (/^\
    0.43
    ウ
    0.43
    renderCamera
    0.42
    Һ
    0.42
    POSITIVE LOGITS
     WAT
    0.59
     tí
    0.45
     glycos
    0.45
     Role
    0.44
    ؛
    0.44
     sympt
    0.43
     Ereign
    0.42
     alk
    0.42
     INSTR
    0.42
     algoritmo
    0.42
    Activations Density 0.001%

    No Known Activations