© 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. 7-GEMMASCOPE-2-RES-16K
    7. 10524
    Prev
    Next
    INDEX
    Explanations

    saving and running code

    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_7_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
    ,
    1.23
     è
    1.18
     não
    1.13
     bia
    1.12
     é
    1.10
     Não
    1.10
     وأ
    1.08
     يحت
    1.07
     بإ
    1.07
     là
    1.07
    POSITIVE LOGITS
    wau
    1.02
    timers
    0.99
    quir
    0.99
     উঠলাম
    0.98
    melden
    0.97
    chaoxing
    0.97
    ifl
    0.96
    hets
    0.96
    ugh
    0.96
    ڃ
    0.95
    Activations Density 0.547%

    No Known Activations