© 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. 61528
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    words following colons or specific prepositions

    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
    چ
    0.46
    '
    0.44
    وا
    0.44
    انی
    0.44
    大規模
    0.44
    (\
    0.44
     Mapping
    0.44
    فر
    0.43
     Districts
    0.42
    ع
    0.42
    POSITIVE LOGITS
    comer
    0.53
     φι
    0.52
     siphon
    0.50
     φυ
    0.49
     জন্যে
    0.49
     되
    0.48
    lín
    0.48
    äude
    0.48
     المالية
    0.47
    pInBuffer
    0.46
    Activations Density 0.000%

    No Known Activations