© 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. 1806
    Prev
    Next
    INDEX
    Explanations

    continue to next

    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
    جم
    1.23
    𝘩
    1.23
    HOLD
    1.18
    counters
    1.18
     rozs
    1.17
    
    1.16
    HISTORY
    1.14
    counter
    1.13
    ł
    1.13
    История
    1.12
    POSITIVE LOGITS
     번째
    1.97
     iteration
    1.85
    쨰
    1.78
     quarter
    1.74
     consecutive
    1.71
    번째
    1.63
    ousand
    1.63
     quartile
    1.62
     degree
    1.61
     successive
    1.59
    Activations Density 0.286%

    No Known Activations