© 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. 40-GEMMASCOPE-2-RES-65K
    7. 50285
    Prev
    Next
    INDEX
    Explanations

    explaining estimates or difficulties

    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_40_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
    畤
    0.44
    ဖ
    0.39
    🏚
    0.39
     segala
    0.39
    νή
    0.39
    機構
    0.38
    GOR
    0.38
    チン
    0.37
    哐
    0.37
     அறிய
    0.37
    POSITIVE LOGITS
    əl
    0.42
     promet
    0.41
     inscre
    0.40
    ids
    0.39
     vende
    0.39
     prioritize
    0.39
     reembol
    0.39
     prefer
    0.38
     আর্জেন্ট
    0.38
     must
    0.38
    Activations Density 0.001%

    No Known Activations