© 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-262K
    7. 110980
    Prev
    Next
    INDEX
    Explanations

    code components and keywords

    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_262k_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
     freelance
    0.44
     probably
    0.41
     small
    0.40
     possess
    0.40
    交
    0.39
     Glock
    0.38
    வை
    0.38
     వైద్య
    0.38
     fonctionne
    0.37
     Sing
    0.37
    POSITIVE LOGITS
    totime
    0.42
    weds
    0.40
    ೪
    0.39
     करने
    0.39
    鄂
    0.38
    IRONMENT
    0.38
     〢
    0.37
    謨
    0.37
    ISHED
    0.37
    nicheskij
    0.37
    Activations Density 0.000%

    No Known Activations