© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13352
    Prev
    Next
    INDEX
    Explanations

    President of

    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
     רא
    2.09
    ⃘
    2.00
    喱
    1.91
     sepatu
    1.87
    doctrine
    1.86
     אם
    1.83
    ੍ਹ
    1.78
     loadChildren
    1.77
    NEY
    1.76
     kor
    1.72
    POSITIVE LOGITS
    eee
    2.08
    eeee
    2.02
    cí
    2.00
    顗
    1.95
    おい
    1.94
    ansch
    1.91
    entation
    1.88
    новні
    1.87
    assium
    1.87
     unsettled
    1.87
    Activations Density 0.092%

    No Known Activations