© 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. 21910
    Prev
    Next
    INDEX
    Explanations

    multilingual concepts and expressions

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

    quotes from and about people

    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
    Genre
    0.41
    GUN
    0.40
    μεν
    0.39
    }[
    0.36
    Berlin
    0.36
    ĕ
    0.35
    鸦
    0.35
    Gün
    0.35
    Men
    0.34
    InfoWindow
    0.34
    POSITIVE LOGITS
    <unused2019>
    0.46
     சிறப்பாக
    0.45
     दट
    0.45
     utilisent
    0.45
    <unused99>
    0.45
     उत्तम
    0.44
     extravagant
    0.44
     Obtaining
    0.44
     يساوي
    0.43
     “,
    0.43
    Activations Density 0.000%

    No Known Activations