© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 109816
    Prev
    Next
    INDEX
    Explanations

    UPI and weather forecasts

    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
    チ
    0.57
    প
    0.57
    지
    0.57
     då
    0.56
    ज
    0.56
    ே
    0.56
    म
    0.54
     دە
    0.53
    ை
    0.53
    ژگی
    0.52
    POSITIVE LOGITS
    ranton
    0.50
     antecedent
    0.49
    utel
    0.49
     listopada
    0.48
     randint
    0.48
    rante
    0.47
     предпринима
    0.46
     Brawl
    0.46
    รางวัล
    0.46
    ninger
    0.44
    Activations Density 0.004%

    No Known Activations