© 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. 241372
    Prev
    Next
    INDEX
    Explanations

    party transactions, followed by context

    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
     recklessly
    0.50
    нется
    0.46
     nuts
    0.46
    ণ্য
    0.45
    னே
    0.44
    ከል
    0.44
     ہوسکتا
    0.44
    શ
    0.44
     untouched
    0.43
    ጅም
    0.43
    POSITIVE LOGITS
     اليس
    0.45
    ech
    0.44
     博文
    0.44
    ie
    0.44
    adhan
    0.43
     الدفاع
    0.43
     مرف
    0.43
    2
    0.43
    em
    0.42
     الداله
    0.42
    Activations Density 0.001%

    No Known Activations