© 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. 29260
    Prev
    Next
    INDEX
    Explanations

    rule, matrix, offer letter, encounter

    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
     सगळ्या
    0.50
     quirky
    0.48
     بزرگ
    0.48
     因为
    0.47
     थांब
    0.47
     ද
    0.46
     எல்லாம்
    0.46
     lazy
    0.45
     encourage
    0.44
     tirelessly
    0.44
    POSITIVE LOGITS
    AT
    0.54
    LET
    0.51
    ATHER
    0.46
    וא
    0.45
     лаборатор
    0.44
    Tại
    0.44
    衵
    0.43
     UNDER
    0.43
     DURING
    0.42
    ATORY
    0.42
    Activations Density 0.036%

    No Known Activations