© 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. 14693
    Prev
    Next
    INDEX
    Explanations

    here are resources

    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
    ですので
    1.19
    相关的
    1.17
    มีการ
    1.16
    に関する
    1.15
    についての
    1.14
    /
    1.14
    相应的
    1.14
     /
    1.12
    ต่างๆ
    1.09
    についても
    1.09
    POSITIVE LOGITS
     decena
    1.78
     decenas
    1.77
     meticul
    1.72
     grim
    1.71
     amid
    1.71
     десять
    1.68
     cientos
    1.68
     diez
    1.68
     nueve
    1.68
     whispers
    1.66
    Activations Density 0.184%

    No Known Activations