© 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. 30310
    Prev
    Next
    INDEX
    Explanations

    text file or group catalog

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

    begin or start engaging content

    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
     checkpoints
    0.46
    飲食店
    0.45
    حل
    0.45
    跄
    0.45
    บค้น
    0.43
     hospitals
    0.43
     diagnóstico
    0.43
    ार्क
    0.43
    স্তের
    0.43
     middlewares
    0.42
    POSITIVE LOGITS
     우
    0.55
    emus
    0.50
    E
    0.49
     رحمه
    0.49
    liang
    0.49
    yo
    0.48
    zo
    0.48
    sp
    0.48
    tw
    0.46
    emu
    0.46
    Activations Density 0.000%

    No Known Activations