© 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. 189234
    Prev
    Next
    INDEX
    Explanations

    spinal curvature

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

    data formatting and instructions

    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
     ব্রি
    0.52
    𐱅
    0.49
    肿
    0.48
     ekonomik
    0.47
    dat
    0.47
    ✹
    0.47
    㷅
    0.47
    På
    0.46
    di
    0.46
    िडेट
    0.46
    POSITIVE LOGITS
    ()+"
    0.55
    ла
    0.48
     skillfully
    0.46
     debuting
    0.44
     Casualty
    0.43
     Telegram
    0.42
     debut
    0.42
    인
    0.42
     ويك
    0.41
    게임
    0.41
    Activations Density 0.000%

    No Known Activations