© 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. 224538
    Prev
    Next
    INDEX
    Explanations

    determining eligibility or describing preceding topics

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

    considerations and lists

    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
    بي
    0.53
    ugg
    0.49
    비
    0.47
    Σ
    0.46
    σσ
    0.46
    يطان
    0.44
    unden
    0.44
    ستون
    0.44
    ندق
    0.44
    叩
    0.44
    POSITIVE LOGITS
     børn
    0.52
     `<
    0.50
     każdym
    0.49
     từng
    0.47
     प्रत्येक
    0.46
     ባህ
    0.46
     gauze
    0.46
    ॉक
    0.45
     děti
    0.45
     رعایت
    0.45
    Activations Density 0.000%

    No Known Activations