© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5068
    Prev
    Next
    INDEX
    Explanations

    server start listening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dagegen
    0.62
    så
    0.60
    --->
    0.60
    从来
    0.59
    shakes
    0.59
     versus
    0.59
    -->
    0.59
    =>
    0.58
     Dany
    0.57
     přímo
    0.57
    POSITIVE LOGITS
    St
    0.73
     St
    0.73
     transmit
    0.67
     высокого
    0.66
    chst
    0.66
     Chamber
    0.66
     st
    0.66
    த்து
    0.64
     approval
    0.64
     최고
    0.63
    Activations Density 0.137%

    No Known Activations