© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7293
    Prev
    Next
    INDEX
    Explanations

    urls ending in .org

    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
     golf
    0.32
     summer
    0.28
    ↵
    0.27
    college
    0.27
     company
    0.27
     event
    0.27
     culmination
    0.26
     cycling
    0.26
     airline
    0.26
     terminou
    0.26
    POSITIVE LOGITS
     〢
    0.28
    glichkeiten
    0.28
    堣
    0.28
    expandindo
    0.28
    ꒷
    0.28
    🥺
    0.27
    🟢
    0.27
    以前
    0.27
     TikTok
    0.27
     Tiwari
    0.27
    Activations Density 0.223%

    No Known Activations