© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 1688
    Prev
    Next
    INDEX
    Explanations

    names and surnames

    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
     LaTeX
    0.27
     Soviet
    0.26
     %
    0.26
    ACTER
    0.25
    bytecode
    0.24
     +
    0.24
     Scientology
    0.24
    igenschaften
    0.24
    방법
    0.24
    %
    0.24
    POSITIVE LOGITS
     Imani
    0.26
     Kiara
    0.26
    ন্দ
    0.25
    മി
    0.24
    ajero
    0.24
    ਮ
    0.24
    କ
    0.24
    ahi
    0.24
     izay
    0.24
    িয়া
    0.23
    Activations Density 0.036%

    No Known Activations