© 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. 174196
    Prev
    Next
    INDEX
    Explanations

    Get the

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

    programming language construct access

    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
     takut
    0.40
     دچار
    0.39
     кло
    0.39
    ラー
    0.38
     medo
    0.37
     द्विवेदी
    0.37
    $/.
    0.37
    udev
    0.36
     implode
    0.36
    }--\
    0.36
    POSITIVE LOGITS
    Germ
    0.45
     germ
    0.42
     Germans
    0.41
     Bouquet
    0.40
     Germ
    0.40
     നിങ്ങൾക്ക്
    0.40
    薀
    0.38
    getParameter
    0.38
     ওয়ালপেপার
    0.37
    getProgress
    0.37
    Activations Density 0.001%

    No Known Activations