© 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. 195010
    Prev
    Next
    INDEX
    Explanations

    languages and scripts

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

    multilingual contexts or specific phrases

    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
     n
    0.49
     נ
    0.47
    u
    0.46
     mungkin
    0.45
    ൂപ
    0.45
     הכ
    0.44
     berjudul
    0.43
     nourrice
    0.43
     ה
    0.42
     سوق
    0.42
    POSITIVE LOGITS
    dde
    0.46
     دوسرے
    0.45
    deps
    0.45
    nici
    0.44
    সংঘ
    0.44
    лем
    0.43
    Entity
    0.43
    áci
    0.43
    ニコ
    0.43
     umano
    0.43
    Activations Density 0.001%

    No Known Activations