© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144289
    Prev
    Next
    INDEX
    Explanations

    actions, prompted, windows, validation, legitimacy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pushbutton
    0.43
    т
    0.42
    柵
    0.41
     Expos
    0.40
    ूज
    0.40
     czemu
    0.40
    goto
    0.39
    Bueno
    0.39
     ahuv
    0.39
    ت
    0.39
    POSITIVE LOGITS
    YPE
    0.46
     πρέπει
    0.46
     প্রয়োগ
    0.45
     Disability
    0.44
     अणुओं
    0.43
     Valence
    0.42
     ਕੋ
    0.41
     stren
    0.41
     Boxing
    0.41
     зре
    0.41
    Activations Density 0.002%

    No Known Activations