© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1682
    Prev
    Next
    INDEX
    Explanations

    end of clause or statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    '=>'
    0.53
    <unused100>
    0.52
    <unused99>
    0.51
    <unused2185>
    0.51
     filesystem
    0.48
    <unused661>
    0.48
    /{
    0.48
    AsyncKeyState
    0.47
     nonlinearity
    0.47
    <unused294>
    0.47
    POSITIVE LOGITS
    Ibid
    0.60
    However
    0.58
     However
    0.57
     Ibid
    0.55
    emphasis
    0.53
    continues
    0.53
     .
    0.51
    Residents
    0.50
     ஆகவே
    0.49
     Residents
    0.48
    Activations Density 0.054%

    No Known Activations