© 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. 88119
    Prev
    Next
    INDEX
    Explanations

    young man, Malcolm, tables, production, persona

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

    maintain character and examples

    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
     sandal
    0.48
    3
    0.48
    raising
    0.46
     اوم
    0.46
    honey
    0.45
     sib
    0.45
     نی
    0.44
     migration
    0.44
     antennes
    0.44
     migrations
    0.43
    POSITIVE LOGITS
     ছেলেদের
    0.50
     கண்டுபிடிக்க
    0.48
    ずつ
    0.46
     championed
    0.46
    供給
    0.45
     යන
    0.45
    \},\{
    0.45
     〢
    0.44
    दिया
    0.44
     देओल
    0.44
    Activations Density 0.000%

    No Known Activations