© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10737
    Prev
    Next
    INDEX
    Explanations

    kms key id

    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
     einde
    1.66
     Midlands
    1.61
     comprov
    1.60
     বোঝা
    1.53
    ção
    1.52
     comprob
    1.52
     pomeriggio
    1.51
    <unused1140>
    1.50
     Medio
    1.48
    surprisingly
    1.48
    POSITIVE LOGITS
    フィー
    1.51
     혁
    1.48
     크
    1.44
     진행
    1.39
    륨
    1.34
     특징
    1.34
     제작
    1.32
     출시
    1.28
     시
    1.25
     radii
    1.25
    Activations Density 0.000%

    No Known Activations