© 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. 247512
    Prev
    Next
    INDEX
    Explanations

    words before punctuation

    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
    Ụ
    0.48
     인증
    0.47
    upply
    0.47
    গ্রাফ
    0.46
    ㈤
    0.46
    叅
    0.46
     Paglinawan
    0.46
     Suède
    0.46
     Logos
    0.45
    রাও
    0.45
    POSITIVE LOGITS
    ют
    0.50
    ळ्या
    0.49
    屯
    0.47
    هم
    0.46
    武器
    0.45
    Balls
    0.45
    奇
    0.44
    、
    0.44
    事を
    0.44
    नई
    0.43
    Activations Density 0.000%

    No Known Activations