© 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. 65512
    Prev
    Next
    INDEX
    Explanations

    i ==

    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
     threshold
    0.44
     sert
    0.44
     ultimo
    0.43
    ultimo
    0.42
    Х
    0.42
     somente
    0.42
    ewhat
    0.42
    מו
    0.42
     JSTOR
    0.41
    <0xB5>
    0.41
    POSITIVE LOGITS
     fejleszt
    0.40
     ች
    0.40
     Admissions
    0.40
     defects
    0.39
     प्रतिद्व
    0.38
     defect
    0.37
     توان
    0.37
    defect
    0.37
    bil
    0.35
     पैमाने
    0.35
    Activations Density 0.012%

    No Known Activations