© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 87307
    Prev
    Next
    INDEX
    Explanations

    official approvals

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

    dopamine synthesis

    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
    锛
    0.45
     Uri
    0.44
    ال
    0.42
     Usuario
    0.42
     Direkt
    0.42
    此类
    0.42
     Alyssa
    0.42
     Beatriz
    0.41
    اول
    0.41
    は
    0.41
    POSITIVE LOGITS
    rega
    0.53
    rā
    0.50
    ounced
    0.49
    ASHI
    0.48
    recl
    0.47
    mada
    0.47
    revise
    0.46
    POSED
    0.46
    restrial
    0.46
    vae
    0.46
    Activations Density 0.001%

    No Known Activations