© 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. 17616
    Prev
    Next
    INDEX
    Explanations

    conjunctions and relative pronouns

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

    conjunctions and verb endings

    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
    يت
    0.49
    یب
    0.48
    (
    0.48
    +
    0.47
    <
    0.46
    ی
    0.44
    >
    0.43
    ્લે
    0.41
    yste
    0.41
    闭
    0.41
    POSITIVE LOGITS
     এবং
    0.64
     אשר
    0.63
     જેમાં
    0.62
     ซึ่ง
    0.61
     which
    0.61
     ਅਤੇ
    0.59
    ซึ่ง
    0.59
     மற்றும்
    0.54
     અને
    0.54
     जिसमें
    0.52
    Activations Density 0.000%

    No Known Activations