© 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. 22400
    Prev
    Next
    INDEX
    Explanations

    more followed by punctuation

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

    and more

    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
     आणि
    0.86
     و
    0.82
     ও
    0.79
     และ
    0.75
     и
    0.74
     and
    0.72
    และ
    0.71
     һәм
    0.71
     किंवा
    0.70
     और
    0.69
    POSITIVE LOGITS
    வற்ற
    0.65
    تي
    0.58
    lerinde
    0.56
    ன்க
    0.54
    lerinin
    0.53
    lerde
    0.51
    лся
    0.50
     in
    0.50
    徒歩
    0.49
    !
    0.49
    Activations Density 0.047%

    No Known Activations