© 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. 868
    Prev
    Next
    INDEX
    Explanations

    monetary values and ranges

    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
     ২
    0.57
    粦
    0.56
    Reminder
    0.56
    +)
    0.54
    ২
    0.54
    ｂ
    0.54
     ৩
    0.53
     itr
    0.52
    +")
    0.52
    Subtract
    0.52
    POSITIVE LOGITS
     multimillion
    0.73
     multifaceted
    0.64
     Million
    0.62
     Norman
    0.61
     weighty
    0.59
     Hobson
    0.59
    <unused184>
    0.57
     domicile
    0.55
     disability
    0.54
     Publications
    0.54
    Activations Density 0.393%

    No Known Activations