© 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. 143378
    Prev
    Next
    INDEX
    Explanations

    claim in accordance with

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

    technical terms and code

    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
    RecordPtr
    0.47
     نیند
    0.47
    時候
    0.46
    picks
    0.46
     rè
    0.45
    ুইস
    0.45
    NESDAY
    0.44
    🥬
    0.43
     ভেদ
    0.43
    ১২
    0.43
    POSITIVE LOGITS
     Desktop
    0.52
     Simple
    0.50
     High
    0.50
     DirectX
    0.48
     Linux
    0.47
     OpenGL
    0.47
     Liga
    0.47
     prati
    0.47
     Hyper
    0.46
     desktop
    0.44
    Activations Density 0.002%

    No Known Activations