© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 249
    Prev
    Next
    INDEX
    Explanations

    would like to try

    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
    <unused996>
    0.94
    <unused231>
    0.93
    㓞
    0.90
    <unused1973>
    0.89
    <unused224>
    0.86
    <unused328>
    0.86
    䏌
    0.85
    <unused1047>
    0.85
    䚯
    0.85
    <unused2041>
    0.85
    POSITIVE LOGITS
    <eos>
    5.84
    ៕
    2.15
    ↵↵↵↵↵↵↵↵↵
    1.80
    ↵↵↵↵↵↵↵↵↵↵
    1.76
    ↵↵↵↵↵↵↵
    1.75
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.74
    ↵↵↵↵↵↵
    1.73
    ↵↵↵↵↵↵↵↵
    1.69
    ↵↵↵↵↵
    1.69
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.68
    Activations Density 5.287%

    No Known Activations