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. 16-GEMMASCOPE-2-RES-262K
    4. 20240
    Prev
    Next
    INDEX
    Explanations

    steps: or category:

    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_16_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
    ü
    0.64
    िन
    0.57
    ী
    0.55
    ক
    0.55
    א
    0.54
    TIME
    0.53
    ন
    0.52
    MAKE
    0.51
    тернет
    0.51
    THA
    0.51
    POSITIVE LOGITS
     misfort
    0.54
    <0x8C>
    0.50
    funding
    0.49
    uere
    0.49
    ially
    0.49
     එය
    0.48
    S
    0.48
    paren
    0.47
    cery
    0.47
     آن
    0.47
    Activations Density 0.000%

    No Known Activations