© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4065
    Prev
    Next
    INDEX
    Explanations

    do you, as to, going to, do not

    np_acts-logits-general · gemini-2.5-flash-lite

    reach out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ๒
    0.48
     সর্বদা
    0.47
     আশ্বাস
    0.46
     ಅಪಾಯ
    0.46
     hinzufügen
    0.46
    উল্লেখ
    0.45
     ವಿವಿಧ
    0.45
    কোনও
    0.45
    ೨
    0.45
    covariant
    0.44
    POSITIVE LOGITS
     it
    0.72
    0.70
     was
    0.62
     they
    0.57
     is
    0.54
     the
    0.52
     had
    0.52
     out
    0.52
     to
    0.49
     The
    0.47
    Activations Density 0.359%

    No Known Activations