© 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. 98736
    Prev
    Next
    INDEX
    Explanations

    styles, place, celebrated, aged

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

    question/options/assess

    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
    У
    0.55
     имущества
    0.52
     calculado
    0.48
     добре
    0.47
    ᒪ
    0.46
    色々
    0.46
    мага
    0.46
    主机
    0.45
    Н
    0.45
     لیګ
    0.45
    POSITIVE LOGITS
     Drug
    0.46
     Airline
    0.46
     fünf
    0.46
     전략
    0.45
     Lovers
    0.43
     Science
    0.42
     Garlic
    0.42
     Jewish
    0.42
     cinq
    0.42
     Physician
    0.42
    Activations Density 0.000%

    No Known Activations