© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27341
    Prev
    Next
    INDEX
    Explanations

    afternoon

    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
     akong
    0.45
     بیت
    0.44
     ব্যাংক
    0.44
     توسیع
    0.43
     incipient
    0.43
    摒
    0.43
    pres
    0.42
     piggy
    0.42
    kerchief
    0.42
     बारह
    0.42
    POSITIVE LOGITS
    ]['
    0.52
     Spinach
    0.48
    )(
    0.46
    ൫
    0.46
    .(
    0.45
    transferase
    0.45
    旪
    0.45
     of
    0.44
    ')
    0.43
    acent
    0.42
    Activations Density 0.003%

    No Known Activations