© 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. 1313
    Prev
    Next
    INDEX
    Explanations

    numbered lists and plans

    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
     accordingly
    0.65
     नाल
    0.57
     straight
    0.56
    손
    0.56
     neither
    0.55
     nrows
    0.55
     consequently
    0.55
     निर्वाचन
    0.54
     უნდა
    0.53
    を入れて
    0.53
    POSITIVE LOGITS
    <unused1443>
    1.07
    subsubsection
    0.81
    책
    0.67
    アクセサリー
    0.66
     బ్రిటి
    0.66
    orgen
    0.66
    subsection
    0.66
    <h3>
    0.65
     Hø
    0.65
    ウォ
    0.64
    Activations Density 0.050%

    No Known Activations