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. 20431
    Prev
    Next
    INDEX
    Explanations

    exported from

    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
    e
    0.61
    ې
    0.61
    制度
    0.60
     vibr
    0.59
     problemat
    0.59
    a
    0.59
     potencialmente
    0.59
    事
    0.58
     diferenci
    0.57
    域
    0.57
    POSITIVE LOGITS
    ()),
    0.67
    '),
    0.57
    つけて
    0.52
    oleh
    0.52
    ཋ
    0.50
    Recipes
    0.50
     क्वे
    0.50
    icast
    0.49
     Uncle
    0.48
    öffent
    0.48
    Activations Density 0.000%

    No Known Activations