© 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. 19905
    Prev
    Next
    INDEX
    Explanations

    revolutionized, handles

    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
     prostaglandin
    0.46
     suppression
    0.45
     پیشنه
    0.44
     coerc
    0.43
    ChooserView
    0.43
     hourglass
    0.42
    辔
    0.42
    条款
    0.42
    ശേഷം
    0.42
    Town
    0.42
    POSITIVE LOGITS
     dará
    0.52
    .)
    0.45
     killing
    0.43
     comput
    0.43
     আম
    0.41
     miała
    0.41
     ama
    0.41
    atile
    0.41
     öld
    0.40
    ۔
    0.40
    Activations Density 0.026%

    No Known Activations