© 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. 251758
    Prev
    Next
    INDEX
    Explanations

    Mule, crisis, table, CV

    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
     PDE
    0.49
     S
    0.46
     P
    0.45
    af
    0.45
     বিপর
    0.44
     upkeep
    0.43
     Mfg
    0.43
    。
    0.43
     crappy
    0.42
     maladies
    0.42
    POSITIVE LOGITS
    𝙢
    0.54
    лина
    0.54
    forbidden
    0.54
    𝘵
    0.52
    тою
    0.50
    equivalence
    0.50
    ∝
    0.49
    ってくる
    0.48
     リン
    0.48
    леко
    0.47
    Activations Density 0.001%

    No Known Activations