© 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. 58326
    Prev
    Next
    INDEX
    Explanations

    specific dates or numbers

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

    modifying code

    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
     распоря
    0.56
     каждую
    0.51
     Habs
    0.47
    拠
    0.46
    សម្រាប់ការ
    0.46
     расположены
    0.46
     Ahí
    0.45
     मुख्यालय
    0.44
     помимо
    0.44
     боя
    0.43
    POSITIVE LOGITS
     }-
    0.44
     smile
    0.43
     negative
    0.42
     error
    0.41
     ผ
    0.40
     discomfort
    0.40
     is
    0.40
     syndrome
    0.40
     조건
    0.40
     misguided
    0.40
    Activations Density 0.000%

    No Known Activations