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. 13878
    Prev
    Next
    INDEX
    Explanations

    advantage or edge

    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
     are
    0.88
    -
    0.84
    in
    0.80
     Comedy
    0.75
    the
    0.73
    '
    0.73
     Ball
    0.71
     Orange
    0.69
     Hurricane
    0.69
     N
    0.68
    POSITIVE LOGITS
    ل
    0.71
    你
    0.70
    )$
    0.67
     ότι
    0.66
     honti
    0.66
     byly
    0.65
     fácilmente
    0.64
     liczb
    0.61
     poveć
    0.61
    办法
    0.61
    Activations Density 0.005%

    No Known Activations