© 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. 94276
    Prev
    Next
    INDEX
    Explanations

    completion

    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
     एकजुट
    0.46
    мой
    0.44
    大人
    0.43
     পল্ল
    0.41
    கரு
    0.39
    よかった
    0.38
    굳
    0.38
    羿
    0.38
     প্রতীক
    0.38
    મિક
    0.38
    POSITIVE LOGITS
     bullets
    0.48
    owego
    0.48
     शांत
    0.48
     Deutsche
    0.47
     pubescence
    0.46
     disobedience
    0.45
    !!.
    0.44
     Fluorescence
    0.44
    io
    0.44
     చేస్తే
    0.44
    Activations Density 0.000%

    No Known Activations