© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9243
    Prev
    Next
    INDEX
    Explanations

    concerns or

    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
     (
    0.82
     Gl
    0.75
     Safety
    0.71
     평
    0.70
    平
    0.70
    Sac
    0.69
    减
    0.67
    立
    0.66
    Safety
    0.66
     Great
    0.65
    POSITIVE LOGITS
     metodi
    0.99
     busiest
    0.97
     codewords
    0.96
     yöntem
    0.96
    inodes
    0.95
     ants
    0.94
     method
    0.94
     contened
    0.94
    sorted
    0.94
     smelly
    0.94
    Activations Density 0.001%

    No Known Activations