© 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-262K
    7. 77100
    Prev
    Next
    INDEX
    Explanations

    check availability or current information

    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
    ul
    0.48
    ява
    0.48
    ᄋ
    0.47
    \">\
    0.46
     vakar
    0.46
    ulk
    0.45
    š
    0.45
    ዎቹ
    0.44
    кир
    0.44
     thug
    0.44
    POSITIVE LOGITS
     he
    0.48
    e
    0.46
     or
    0.44
    de
    0.43
     on
    0.43
     yet
    0.43
    เข
    0.43
    Sph
    0.42
     it
    0.42
    为
    0.41
    Activations Density 0.008%

    No Known Activations