© 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. 14419
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    breakdown of explanations or lists

    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
    \*
    0.56
    6
    0.52
    ION
    0.49
     بيان
    0.49
     виду
    0.49
    \
    0.48
    OND
    0.47
    undle
    0.47
    /
    0.46
    l
    0.46
    POSITIVE LOGITS
    धनों
    0.56
     கெல்வின்
    0.49
    天気
    0.49
     mej
    0.48
     culinary
    0.48
     dilihat
    0.48
    ฝ
    0.47
    ঘন
    0.46
     महत्
    0.45
     munk
    0.45
    Activations Density 0.000%

    No Known Activations