© 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. 209505
    Prev
    Next
    INDEX
    Explanations

    words following punctuation

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

    either mistaken or ignorant

    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
    ",[(
    0.54
    نین
    0.51
     constricted
    0.50
    하십시오
    0.49
    を表
    0.48
    ಿದ
    0.48
     varia
    0.48
    에게
    0.47
    無い
    0.47
    풍
    0.47
    POSITIVE LOGITS
    ub
    0.57
     Congressional
    0.55
    ur
    0.49
     Council
    0.48
     ওজন
    0.48
     Weight
    0.47
     softball
    0.47
     potential
    0.46
     Quarry
    0.46
     Assembly
    0.46
    Activations Density 0.001%

    No Known Activations