© 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. 32128
    Prev
    Next
    INDEX
    Explanations

    verbs of cognition and intention

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

    countering opponents

    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
    3
    0.45
    correspond
    0.43
     혹은
    0.42
    CCC
    0.42
     watu
    0.41
     have
    0.41
     corresponding
    0.41
    corresponding
    0.41
    〇
    0.40
     준
    0.39
    POSITIVE LOGITS
    他说
    0.49
    他說
    0.49
    他不
    0.48
     деятельность
    0.46
    我现在
    0.46
    തെന്നും
    0.45
    赭
    0.44
    她说
    0.43
     શિક્ષણ
    0.43
     ویب
    0.42
    Activations Density 0.000%

    No Known Activations