© 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. 217294
    Prev
    Next
    INDEX
    Explanations

    toss all, be leaders, reporting units

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

    static, time, PCB, AI

    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
    is
    0.54
    Algorithm
    0.54
    Creation
    0.48
     Ouverture
    0.48
     Establishment
    0.48
     બધા
    0.48
     Whiskey
    0.48
     Y
    0.46
    Reducer
    0.46
    欴
    0.46
    POSITIVE LOGITS
    ینو
    0.52
     fnt
    0.50
    수한
    0.49
    ،
    0.47
     tomó
    0.46
    '،
    0.46
    ༸
    0.46
    、
    0.45
     într
    0.45
    нет
    0.44
    Activations Density 0.000%

    No Known Activations