© 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. 178941
    Prev
    Next
    INDEX
    Explanations

    predicts and follows

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

    focus on, gotta do, seamlessly with

    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
    usepackage
    0.45
    ");
    0.45
     NRL
    0.45
    <0xE3>
    0.44
    eroy
    0.44
    م
    0.44
    ，
    0.44
    toctree
    0.43
    レ
    0.43
    erry
    0.42
    POSITIVE LOGITS
     என்பது
    0.55
     иначе
    0.52
     совсем
    0.51
    भंगा
    0.51
     बंदी
    0.51
    ങ്ങൾക്ക്
    0.48
     Елена
    0.48
    खण्ड
    0.47
    HTTPSampler
    0.47
     своём
    0.47
    Activations Density 0.000%

    No Known Activations