© 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. 59636
    Prev
    Next
    INDEX
    Explanations

    language, file, and technical terms

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

    sine wave amplitude

    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
    ີ
    0.57
    ີ້
    0.49
     теннис
    0.49
     Bül
    0.47
    রত
    0.47
    erçe
    0.47
    MenuList
    0.47
    ลักษณ์
    0.47
     Alpes
    0.47
    ственные
    0.46
    POSITIVE LOGITS
     幅
    0.55
     aria
    0.44
     যাবতীয়
    0.42
     filename
    0.42
    fera
    0.40
     فائلوں
    0.40
    FileSystem
    0.40
     فایل
    0.40
     hela
    0.39
    bohyd
    0.39
    Activations Density 0.001%

    No Known Activations