© 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. 97717
    Prev
    Next
    INDEX
    Explanations

    goals, substance, and dangerous products

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

    keywords at start of phrases

    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
    м
    0.50
    й
    0.49
     leaks
    0.48
    נ
    0.48
    م
    0.48
     abuses
    0.47
    僥
    0.46
    atletas
    0.46
    ષ્ણા
    0.46
    в
    0.45
    POSITIVE LOGITS
     Electrical
    0.50
     Elektro
    0.50
     UST
    0.48
     uczni
    0.47
     ഉപകരണ
    0.47
    AppData
    0.46
     স্টি
    0.46
     Groundwater
    0.46
     Shred
    0.45
     viš
    0.45
    Activations Density 0.000%

    No Known Activations