© 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. 32415
    Prev
    Next
    INDEX
    Explanations

    rhythmic massage

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

    "with number" and "on behalf of"

    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
    a
    0.50
    ud
    0.47
    getEstado
    0.45
     mandato
    0.44
    entre
    0.44
    parse
    0.44
    룻
    0.43
     vacuna
    0.43
    擾
    0.42
    audi
    0.42
    POSITIVE LOGITS
     ঈ
    0.54
     Seahawks
    0.53
     .$
    0.50
     NVARCHAR
    0.50
     সাগর
    0.48
    ంక
    0.48
     ACTION
    0.47
     ชั้น
    0.47
     AGAINST
    0.47
     LAKE
    0.47
    Activations Density 0.000%

    No Known Activations