© 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. 1949
    Prev
    Next
    INDEX
    Explanations

    quoted character identifiers

    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
    マリン
    0.67
     ancien
    0.65
     Coleman
    0.63
    4
    0.61
     Hodgson
    0.61
    ۲۰
    0.60
    श्य
    0.60
     Marques
    0.59
    serrat
    0.59
     Vier
    0.59
    POSITIVE LOGITS
     z
    0.95
     u
    0.83
    z
    0.82
    ｚ
    0.82
     y
    0.77
    ｘ
    0.77
     w
    0.76
     g
    0.76
     k
    0.74
     q
    0.73
    Activations Density 0.076%

    No Known Activations