© 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. 212970
    Prev
    Next
    INDEX
    Explanations

    foreign script and words

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

    metroidvania discussions

    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
    ходил
    0.46
     코드
    0.46
     ifades
    0.45
    This
    0.45
     иностран
    0.44
    Greetings
    0.44
    禊
    0.44
     io
    0.43
    ♗
    0.43
     कोड
    0.43
    POSITIVE LOGITS
    şam
    0.50
    لیسی
    0.48
    ઝા
    0.48
    ponsor
    0.47
     ケ
    0.45
    aków
    0.45
    ঙ্গে
    0.44
    écut
    0.44
    ಸ್‌
    0.44
    stic
    0.44
    Activations Density 0.001%

    No Known Activations