© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 45036
    Prev
    Next
    INDEX
    Explanations

    custom sense engine

    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
     insignia
    0.47
     시작하겠습니다
    0.44
    stö
    0.44
     headsets
    0.44
     annoy
    0.43
    rosis
    0.43
    \}
    0.42
     almac
    0.42
     insult
    0.41
     prossima
    0.41
    POSITIVE LOGITS
     MICHIGAN
    0.44
     přímo
    0.43
    ឿង
    0.43
    望
    0.41
     alebo
    0.41
    acyjnego
    0.41
    anjem
    0.41
    érien
    0.41
     महज
    0.40
    ционно
    0.40
    Activations Density 0.003%

    No Known Activations