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. 11171
    Prev
    Next
    INDEX
    Explanations

    variable assignment and code structure

    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
    all
    0.64
     ,
    0.63
     all
    0.60
     semua
    0.60
    most
    0.58
    pink
    0.57
    new
    0.56
    this
    0.56
    dropBtn
    0.56
    objects
    0.55
    POSITIVE LOGITS
     difficoltà
    0.70
    פ
    0.69
    י
    0.69
    ח
    0.68
    ι
    0.66
    น
    0.64
    ειτουργ
    0.63
     розвитку
    0.62
    ниці
    0.60
    বীর
    0.60
    Activations Density 0.063%

    No Known Activations