© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 24527
    Prev
    Next
    INDEX
    Explanations

    so no

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

    replacing epsagon or why balance not updated

    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
     เกม
    0.52
     この
    0.51
     งาน
    0.50
     godina
    0.50
     点
    0.49
    okas
    0.49
     conveniently
    0.47
    ką
    0.47
     पेपर
    0.47
     図
    0.46
    POSITIVE LOGITS
    revoke
    0.46
    عى
    0.45
    עי
    0.45
    ܥ
    0.44
    вич
    0.44
    ّى
    0.43
     процен
    0.43
    აცი
    0.42
    ა
    0.42
    ев
    0.41
    Activations Density 0.000%

    No Known Activations