© 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. 164098
    Prev
    Next
    INDEX
    Explanations

    enthusiastic exclamation marks

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

    clearly stating your consequences

    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
    이를
    0.49
     int
    0.49
    '
    0.49
    arı
    0.48
    s
    0.47
     protesting
    0.47
    k
    0.46
    ént
    0.45
     inex
    0.45
     dost
    0.44
    POSITIVE LOGITS
    MOUNTAINS
    0.59
    ONDER
    0.51
    ラ
    0.46
     अराउंड
    0.44
    пут
    0.44
    部は
    0.44
    わた
    0.44
     聞い
    0.43
     三菱
    0.43
    যানী
    0.43
    Activations Density 0.000%

    No Known Activations