© 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. 244381
    Prev
    Next
    INDEX
    Explanations

    like kinetic quarry drum advance western minute

    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
    垲
    0.53
    餸
    0.53
    俅
    0.49
    洴
    0.48
    Ꭽ
    0.47
    Ꮴ
    0.47
    名稱
    0.46
    궬
    0.46
    <unused32>
    0.46
     SEQ
    0.46
    POSITIVE LOGITS
    iness
    0.54
    TT
    0.52
    ”
    0.52
    ery
    0.51
    aka
    0.50
    >
    0.49
    ↵
    0.49
    ses
    0.49
    </b>
    0.49
    esi
    0.48
    Activations Density 0.000%

    No Known Activations