© 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. 40588
    Prev
    Next
    INDEX
    Explanations

    experience with specific roles

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

    phrases or context

    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
    l
    0.47
    antique
    0.46
    r
    0.45
     மீன
    0.44
    7
    0.44
    zoa
    0.43
     Klein
    0.43
     Principe
    0.43
     Netherlands
    0.43
    lvl
    0.43
    POSITIVE LOGITS
    рую
    0.52
     μή
    0.51
    '$\
    0.48
    ங்குக
    0.46
     ALSO
    0.46
     десятки
    0.45
    時間を
    0.45
    書き
    0.44
    प्
    0.44
     endTime
    0.44
    Activations Density 0.000%

    No Known Activations