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. 797
    Prev
    Next
    INDEX
    Explanations

    cause, condition, basis

    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
    루
    0.74
     Really
    0.74
     Five
    0.73
     Be
    0.72
    वों
    0.71
     One
    0.70
     Must
    0.70
    厮
    0.70
    یو
    0.70
     rimane
    0.70
    POSITIVE LOGITS
     प्रोत्साहित
    0.97
     newLine
    0.93
    perturbed
    0.90
     oscillations
    0.89
     photosynthesis
    0.88
     enteric
    0.88
     perturbations
    0.87
     thickening
    0.86
    ometries
    0.86
     broadening
    0.85
    Activations Density 0.956%

    No Known Activations