© 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. 62032
    Prev
    Next
    INDEX
    Explanations

    HTML option tags

    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
     nood
    0.44
     prot
    0.44
     prélim
    0.43
    ">⁢</
    0.43
     protocol
    0.40
    ൧
    0.40
     soru
    0.39
    RAchievement
    0.39
     topological
    0.38
    getMainUI
    0.38
    POSITIVE LOGITS
     Carg
    0.43
    artney
    0.39
    stackpath
    0.38
     скло
    0.37
     Nac
    0.37
     નક્કી
    0.37
    美
    0.36
     శక్తి
    0.36
    నాలను
    0.36
     Carre
    0.36
    Activations Density 0.002%

    No Known Activations