© 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. 182385
    Prev
    Next
    INDEX
    Explanations

    meant to substitute

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

    material properties

    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
    오늘은
    0.50
    शाह
    0.50
    시는
    0.48
    బ్బ
    0.48
     Leafs
    0.46
    ໂ
    0.46
    সি
    0.46
    !”
    0.46
     मिली
    0.46
    太子
    0.46
    POSITIVE LOGITS
    heten
    0.50
    ypse
    0.49
    thest
    0.48
     nonthermal
    0.47
     打开
    0.47
    /:
    0.46
     调用
    0.46
     scrubber
    0.46
     fname
    0.45
    nilai
    0.45
    Activations Density 0.001%

    No Known Activations