© 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. 37641
    Prev
    Next
    INDEX
    Explanations

    obtain rare High society caps add image

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

    documentaries, suffering, screens

    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
    GAM
    0.47
    Ә
    0.46
    TS
    0.45
    STOR
    0.45
    ATO
    0.45
    LET
    0.43
    МИ
    0.43
    seit
    0.43
    iters
    0.43
    ALAR
    0.43
    POSITIVE LOGITS
     包括
    0.53
     動物
    0.48
     ekstra
    0.46
     ­
    0.46
    ၊
    0.46
    သည့်
    0.45
     ឬ
    0.45
     ကု
    0.44
    ပါသည်။
    0.43
     sprinkled
    0.43
    Activations Density 0.000%

    No Known Activations