© 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. 154390
    Prev
    Next
    INDEX
    Explanations

    severity, expedition, editor

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

    detail examples

    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
    レ
    0.61
    LE
    0.55
    デ
    0.51
    アー
    0.47
    ユニ
    0.46
    セレ
    0.46
    ワー
    0.46
    E
    0.46
    CROSS
    0.46
    テキスト
    0.46
    POSITIVE LOGITS
    berto
    0.49
     भोजपुरी
    0.48
     integrable
    0.47
    vamente
    0.46
     potrà
    0.46
     اقتصاد
    0.46
     можем
    0.45
     produkty
    0.44
    itä
    0.43
     potrebbe
    0.43
    Activations Density 0.000%

    No Known Activations