© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5369
    Prev
    Next
    INDEX
    Explanations

    repeating sequences and punctuation

    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
    Audit
    1.68
    们的
    1.64
    Datasets
    1.62
    Compile
    1.59
    Transactional
    1.58
    <unused2051>
    1.57
    <unused592>
    1.55
    <unused1952>
    1.55
    Bias
    1.54
    Interfaces
    1.54
    POSITIVE LOGITS
     put
    0.97
     -
    0.85
     employs
    0.82
     uses
    0.81
     భాగంగా
    0.81
     ton
    0.80
     mix
    0.79
     involve
    0.76
     goal
    0.75
    0.75
    Activations Density 0.187%

    No Known Activations