© 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. 24787
    Prev
    Next
    INDEX
    Explanations

    affiliation or sponsorship

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

    comparison and description

    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
     przyczyn
    0.51
    债
    0.50
    芗
    0.48
    توان
    0.47
    銆
    0.45
     способствует
    0.45
    Debt
    0.45
    Benefit
    0.45
    贡献
    0.44
    تف
    0.44
    POSITIVE LOGITS
     Siemens
    0.54
    નાં
    0.50
     Rin
    0.48
     "
    0.47
     Stars
    0.47
     Hir
    0.46
     Hasht
    0.46
     Dots
    0.46
     Kanji
    0.46
     The
    0.46
    Activations Density 0.000%

    No Known Activations