© 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. 223988
    Prev
    Next
    INDEX
    Explanations

    phrases with actions and descriptions

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

    levels of complexity

    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
    ری
    0.49
    емые
    0.47
     hôtels
    0.46
    ۰
    0.45
    ඍ
    0.44
    वीय
    0.44
    UserModel
    0.44
     gaps
    0.44
     hoteles
    0.43
     شوی
    0.43
    POSITIVE LOGITS
    ాన్ని
    0.52
    <0xAB>
    0.49
    ir
    0.44
     молодой
    0.44
     하겠습니다
    0.43
    那位
    0.42
     signaler
    0.42
    urrection
    0.42
     압
    0.42
     亻
    0.41
    Activations Density 0.000%

    No Known Activations