© 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. 158187
    Prev
    Next
    INDEX
    Explanations

    multi-language text segmentation

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

    I'll tell you what

    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
    Suit
    0.44
    ।
    0.41
     толькі
    0.41
     lun
    0.41
    改变
    0.40
    iths
    0.40
    改變
    0.39
    LAN
    0.39
    ።
    0.39
    當地
    0.39
    POSITIVE LOGITS
     Văn
    0.61
    লিশ
    0.54
    vvvert
    0.53
     etkinlik
    0.51
    NEY
    0.50
     imprensa
    0.50
     十
    0.50
    াবাহ
    0.49
     legno
    0.49
     çev
    0.48
    Activations Density 0.000%

    No Known Activations