Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 7379
    Prev
    Next
    INDEX
    Explanations

    list items and steps

    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
     voluptates
    0.47
     erfolgen
    0.46
    щается
    0.46
     chapters
    0.45
     Chapters
    0.44
    错了
    0.44
    ล
    0.43
    >'
    0.42
    ض
    0.42
     chis
    0.42
    POSITIVE LOGITS
    still
    0.45
    エク
    0.45
    shipping
    0.45
    FG
    0.44
    shoring
    0.44
    optimal
    0.44
    nessy
    0.42
     FSB
    0.42
    šek
    0.42
    specification
    0.42
    Activations Density 0.111%

    No Known Activations