© 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. 243299
    Prev
    Next
    INDEX
    Explanations

    split, rail, humans, repair, excluding

    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
     앞에
    0.44
     k
    0.43
     kth
    0.42
    k
    0.42
     hammer
    0.40
     pus
    0.40
     hazardous
    0.40
     grammar
    0.40
     poprzed
    0.40
     Hamburg
    0.39
    POSITIVE LOGITS
    聘
    0.48
    ποιή
    0.47
    默默
    0.47
    ቭ
    0.46
    ǯ
    0.46
    認知
    0.46
    Ό
    0.45
    лі
    0.45
     AVER
    0.45
    偐
    0.45
    Activations Density 0.001%

    No Known Activations