© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202405
    Prev
    Next
    INDEX
    Explanations

    names and descriptions that follow punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    。</
    0.44
     timid
    0.41
    。\
    0.41
     contrasted
    0.41
    可能會
    0.40
     contrasts
    0.39
     incompre
    0.38
    Therefore
    0.37
    哈哈哈
    0.37
    xRt
    0.37
    POSITIVE LOGITS
     tenemos
    0.46
     (
    0.46
     I
    0.45
     tengo
    0.45
     আমি
    0.44
     אני
    0.42
     আমরা
    0.41
     kita
    0.40
     Move
    0.39
     그걸
    0.39
    Activations Density 0.009%

    No Known Activations