© 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. 14923
    Prev
    Next
    INDEX
    Explanations

    closing resources after errors

    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
     水
    1.16
    ⓡ
    1.08
     和
    1.07
     gió
    1.07
     而且
    1.06
    andelion
    1.06
     uč
    1.06
    fees
    1.05
     Disputes
    1.05
    水
    1.05
    POSITIVE LOGITS
    ้อมูล
    1.10
     devolved
    1.04
    لومات
    0.98
    هور
    0.98
    হাসিক
    0.95
     insuffisamment
    0.95
    amanya
    0.93
    onial
    0.93
    Спољашње
    0.92
     foli
    0.90
    Activations Density 0.002%

    No Known Activations