© 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. 68993
    Prev
    Next
    INDEX
    Explanations

    modality and optionality

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

    react useContext custom hooks

    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
    Reg
    0.49
    ون
    0.49
    Trans
    0.48
    Device
    0.47
    China
    0.45
    Ukraine
    0.45
    平
    0.44
    Strat
    0.44
    ED
    0.43
    و
    0.43
    POSITIVE LOGITS
     gstlal
    0.53
     යුතුය
    0.52
     යුතු
    0.50
     যথেষ্ট
    0.50
     Hör
    0.48
    lardır
    0.48
     کررہے
    0.48
     sacro
    0.48
    ufficient
    0.47
     astrophys
    0.47
    Activations Density 0.000%

    No Known Activations