© 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. 28799
    Prev
    Next
    INDEX
    Explanations

    Hindi verbs (present/past tense)

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

    habitual or continuous actions

    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
     যাইতে
    0.46
     লইয়
    0.45
    km
    0.44
    KM
    0.44
    Видео
    0.44
     চালানোর
    0.42
    보기
    0.42
    ড
    0.42
    лимпи
    0.41
    보고
    0.41
    POSITIVE LOGITS
     کہ
    0.56
     ਸੁ
    0.55
     परन्तु
    0.54
     apni
    0.48
     hoga
    0.47
     हैं
    0.47
     ਹੈ
    0.46
     cuya
    0.46
     polizia
    0.46
     questioned
    0.45
    Activations Density 0.002%

    No Known Activations