© 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. 1564
    Prev
    Next
    INDEX
    Explanations

    print or log function calls

    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
     ¡
    0.85
     ¿
    0.80
    .$(
    0.74
     چیزی
    0.69
     #####
    0.68
     ¿?
    0.68
     होके
    0.67
     मालिका
    0.67
    ¡
    0.67
    ಲೇ
    0.67
    POSITIVE LOGITS
    ('
    3.36
     ('
    3.10
    ("
    3.08
     (‘
    2.86
     ("
    2.83
    (['
    2.75
    (“
    2.74
     (“
    2.72
    (["
    2.51
    ('/
    2.48
    Activations Density 0.251%

    No Known Activations