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. 36774
    Prev
    Next
    INDEX
    Explanations

    marketing, AI, finding, history

    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
     addBook
    0.50
     pleases
    0.47
     Mbps
    0.46
     nowDate
    0.46
     kwamba
    0.46
    ઞ
    0.46
     книга
    0.46
    न्नाथ
    0.46
     pointA
    0.46
     keuntungan
    0.45
    POSITIVE LOGITS
    har
    0.54
    ors
    0.50
    )
    0.49
    uran
    0.49
    ot
    0.48
    le
    0.47
    hind
    0.47
    ard
    0.47
    xiang
    0.46
    hist
    0.46
    Activations Density 0.000%

    No Known Activations