© 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-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2463
    Prev
    Next
    INDEX
    Explanations

    () and ();

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
    <unused1744>
    0.76
    <unused893>
    0.72
    <unused2222>
    0.70
    <unused948>
    0.67
    <unused2140>
    0.65
    <unused300>
    0.64
    <unused279>
    0.62
    ધું
    0.62
    <unused649>
    0.62
     Moscow
    0.61
    POSITIVE LOGITS
    ／
    0.69
    :///
    0.65
     ()
    0.63
     ();
    0.61
    ();
    0.61
    ّ
    0.61
     ($
    0.61
     ().
    0.60
    ـــ
    0.59
    ():
    0.58
    Activations Density 0.179%

    No Known Activations