© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6901
    Prev
    Next
    INDEX
    Explanations

    quotes for spaces and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     크게
    1.83
    もあり
    1.77
    이지만
    1.76
     많
    1.73
    들도
    1.69
     대표
    1.68
    덧
    1.67
     이게
    1.66
     이상의
    1.66
     자체가
    1.65
    POSITIVE LOGITS
     frequently
    1.60
     accidentally
    1.51
     annually
    1.43
     during
    1.42
     pregnant
    1.37
     promising
    1.36
     anxious
    1.35
     infrequently
    1.34
     rarely
    1.33
     disturbed
    1.33
    Activations Density 0.007%

    No Known Activations