© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 108378
    Prev
    Next
    INDEX
    Explanations

    projects, skills, and goals

    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
    ↵
    0.42
     The
    0.38
     Include
    0.38
     では
    0.36
     Referred
    0.36
     using
    0.34
     referred
    0.33
     the
    0.32
     이
    0.32
     Applied
    0.31
    POSITIVE LOGITS
     धवन
    0.39
    ുണ്ട്
    0.39
     ആണ്
    0.38
     دولار
    0.37
     prefeito
    0.37
     statutes
    0.37
     statute
    0.36
     birkaç
    0.36
    錢
    0.36
     және
    0.36
    Activations Density 0.006%

    No Known Activations