© 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. 26332
    Prev
    Next
    INDEX
    Explanations

    nylon

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

    even if / attempting

    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
    س
    0.46
    រយៈពេល
    0.44
     ogen
    0.42
    实时
    0.39
    فاوت
    0.38
    警方
    0.38
     chẳng
    0.38
    حديد
    0.38
    ाइज
    0.38
    多种
    0.37
    POSITIVE LOGITS
    WCHAR
    0.53
    Glor
    0.46
    Raises
    0.46
    Surname
    0.46
     उपर
    0.45
    ,_
    0.44
     ऊपर
    0.44
     Raises
    0.44
    Harmony
    0.43
     現在
    0.43
    Activations Density 0.000%

    No Known Activations