© 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. 1849
    Prev
    Next
    INDEX
    Explanations

    but

    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
     घेतल्या
    0.76
     :=
    0.66
    呢
    0.66
     wraz
    0.65
    нями
    0.65
    ുകയായിരുന്നു
    0.64
     చేయడం
    0.63
    ými
    0.60
    뭡
    0.60
    ക്കുക
    0.60
    POSITIVE LOGITS
     but
    6.61
    but
    6.26
     nhưng
    5.76
     BUT
    5.64
    但
    5.60
     pero
    5.57
    But
    5.37
     But
    5.31
    BUT
    5.30
     लेकिन
    5.25
    Activations Density 5.316%

    No Known Activations