© 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. 16-GEMMASCOPE-2-RES-262K
    7. 109810
    Prev
    Next
    INDEX
    Explanations

    writing and formatting text

    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
    沄
    0.49
     Fears
    0.49
     Entry
    0.49
     Argument
    0.48
     نقدم
    0.48
     Six
    0.47
    ഖ
    0.47
     Out
    0.46
     Prior
    0.46
    Calcul
    0.46
    POSITIVE LOGITS
     apparaissent
    0.63
    etrot
    0.56
    andinavian
    0.54
     к
    0.50
    arie
    0.49
     américains
    0.49
    {
    0.48
     ontwikk
    0.48
    uede
    0.47
     thermocouple
    0.47
    Activations Density 0.000%

    No Known Activations