© 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. 889
    Prev
    Next
    INDEX
    Explanations

    name or specific word sequences

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

    WebSocket and RTC protocols

    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
    moh
    0.47
    ළු
    0.46
    ዘጋ
    0.46
    located
    0.43
    கடந்த
    0.43
    اج
    0.43
    踺
    0.43
    Shivam
    0.42
    بيع
    0.42
    සිය
    0.41
    POSITIVE LOGITS
    IDTH
    0.50
     amn
    0.48
     η
    0.48
     rilev
    0.47
     sine
    0.46
     yapt
    0.46
     aritm
    0.45
     חש
    0.45
     decimal
    0.45
    OneFrame
    0.45
    Activations Density 0.000%

    No Known Activations