© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 65231
    Prev
    Next
    INDEX
    Explanations

    content dripping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }^{(
    0.37
     យើង
    0.37
    }}$;
    0.36
    $^{
    0.35
    াক্তন
    0.35
    ',[
    0.35
    рім
    0.35
    benzoimidazole
    0.34
    ”—
    0.34
     watt
    0.33
    POSITIVE LOGITS
     ->
    0.37
    en
    0.36
     Fiscalía
    0.36
    という意味
    0.36
     >>
    0.35
     podstawie
    0.35
     en
    0.34
    Lima
    0.34
     Cev
    0.34
    こちらも
    0.34
    Activations Density 0.002%

    No Known Activations