© 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. 134659
    Prev
    Next
    INDEX
    Explanations

    users helping other users

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

    rather than isothermal

    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
    parsed
    0.52
    getInput
    0.52
    ရ
    0.48
    输入的
    0.46
    Uploading
    0.46
    Returned
    0.46
     కారణంగా
    0.46
    cars
    0.46
    ๑
    0.46
    结
    0.45
    POSITIVE LOGITS
     Ley
    0.55
     ante
    0.52
     Ante
    0.51
     Key
    0.50
     gaji
    0.49
     derr
    0.49
     egg
    0.49
     gren
    0.47
     Kali
    0.47
     kri
    0.47
    Activations Density 0.001%

    No Known Activations