Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 1043
    Prev
    Next
    INDEX
    Explanations

    units of length and distance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    a
    0.95
    5
    0.90
    7
    0.88
    0
    0.88
    e
    0.88
    6
    0.83
     que
    0.79
    8
    0.77
    9
    0.76
     malt
    0.75
    POSITIVE LOGITS
     daily
    0.99
    ಷ್ಟು
    0.93
     asymptotically
    0.90
    peres
    0.88
     inland
    0.87
    өз
    0.87
     dzien
    0.84
    illion
    0.84
     frontage
    0.83
    ایر
    0.83
    Activations Density 0.497%

    No Known Activations