© 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. 259
    Prev
    Next
    INDEX
    Explanations

    code syntax and logic

    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
    <h3>
    0.73
    <h2>
    0.70
    <h4>
    0.63
    etc
    0.61
                                   
    0.59
    evším
    0.59
    0.57
    python
    0.57
    <0x0C>
    0.55
    <u>
    0.55
    POSITIVE LOGITS
    ネルギー
    0.72
     interesses
    0.65
    <unused647>
    0.64
     Kabel
    0.63
    輕
    0.61
    <unused305>
    0.61
     readjust
    0.61
     bureau
    0.60
    <unused2104>
    0.60
    <unused756>
    0.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.