© 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. 46676
    Prev
    Next
    INDEX
    Explanations

    lists of bullet points

    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
    NK
    0.49
    MA
    0.48
    J
    0.47
    INO
    0.47
    UT
    0.47
    IP
    0.46
    UR
    0.46
    NI
    0.46
    Y
    0.45
    ového
    0.45
    POSITIVE LOGITS
     جنہوں
    0.57
     décadas
    0.54
     jotka
    0.52
     preocupación
    0.48
     दशकों
    0.48
     quienes
    0.46
     борьбе
    0.46
     контек
    0.45
     contextos
    0.45
     tremend
    0.44
    Activations Density 0.019%

    No Known Activations