© 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. 13749
    Prev
    Next
    INDEX
    Explanations

    script or program language

    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
    ^{[\
    1.20
    ֣
    1.18
     พี่
    1.18
    Phillips
    1.15
    พี่
    1.15
    whose
    1.14
    !“
    1.13
    cof
    1.12
     cof
    1.12
    èbre
    1.09
    POSITIVE LOGITS
     Observations
    1.05
    穿
    1.00
     observations
    0.91
     visualizations
    0.88
     Disbursement
    0.86
     decimals
    0.83
     Seconds
    0.82
     Observed
    0.82
     Machines
    0.82
    前後
    0.81
    Activations Density 0.132%

    No Known Activations