© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15908
    Prev
    Next
    INDEX
    Explanations

    bullets, code, or markdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skills
    0.42
     lì
    0.40
     topical
    0.38
    skills
    0.37
    啧
    0.37
     Washington
    0.36
     সাধন
    0.36
     mV
    0.36
     gir
    0.35
     достой
    0.35
    POSITIVE LOGITS
    עות
    0.42
    дії
    0.42
    պես
    0.41
    <0x93>
    0.41
    ပေ
    0.40
    🔸
    0.40
     प्रहरी
    0.40
    Figure
    0.39
    เด
    0.39
    이스
    0.39
    Activations Density 0.094%

    No Known Activations