© 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. 201155
    Prev
    Next
    INDEX
    Explanations

    against illegal, the airport, in the public domain

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

    possible values, types, or actions

    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
    ب
    0.53
    ława
    0.50
     premieres
    0.47
    ህል
    0.47
     downlink
    0.46
     تابع
    0.46
    গল
    0.46
     ($
    0.45
    ग्रेड
    0.45
    ১
    0.45
    POSITIVE LOGITS
    сіб
    0.50
    ”，
    0.45
    ња
    0.44
     автомобі
    0.44
    擘
    0.44
    ᠮ
    0.44
    сія
    0.43
    qst
    0.42
    вість
    0.42
    roqu
    0.42
    Activations Density 0.000%

    No Known Activations