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. 31-GEMMASCOPE-2-RES-262K
    4. 12111
    Prev
    Next
    INDEX
    Explanations

    words following 'or'

    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_31_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
    i
    0.71
     alebo
    0.68
     ή
    0.68
    ي
    0.68
     или
    0.65
     aŭ
    0.63
    或者
    0.62
     או
    0.61
     arba
    0.60
     ducts
    0.58
    POSITIVE LOGITS
     a
    0.76
    ignal
    0.66
    ients
    0.61
     an
    0.56
    acles
    0.54
    acular
    0.54
     gewoon
    0.53
    踏
    0.53
     electrónico
    0.52
    ակի
    0.52
    Activations Density 0.162%

    No Known Activations