© 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. 61155
    Prev
    Next
    INDEX
    Explanations

    file an, very appealing

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

    negation or conditions

    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
    烏
    0.52
    乌
    0.45
     conquests
    0.44
     bestowed
    0.44
     paramilitary
    0.43
    狩
    0.42
    兔
    0.42
    瑶
    0.40
     affords
    0.40
    多少
    0.39
    POSITIVE LOGITS
    프트
    0.49
    izzando
    0.49
     Experten
    0.48
    เหล่านี้
    0.48
     detto
    0.48
    itato
    0.48
     журнал
    0.47
     ลักษณะ
    0.47
    тировать
    0.47
    opération
    0.46
    Activations Density 0.000%

    No Known Activations