© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43259
    Prev
    Next
    INDEX
    Explanations

    obscure miscellany

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

    asking you for instructions

    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
    jela
    0.49
    }}(\
    0.47
     الشركات
    0.46
     jedoch
    0.45
     Verfahren
    0.45
     empfe
    0.44
     וא
    0.43
    neider
    0.42
     infrastructural
    0.42
     നടത്ത
    0.42
    POSITIVE LOGITS
    ╋
    0.50
    SPC
    0.48
    뭣
    0.48
    विस
    0.48
    饕
    0.45
     дос
    0.45
    伯
    0.45
    樵
    0.45
    Do
    0.45
    Singolare
    0.45
    Activations Density 0.001%

    No Known Activations