© 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. 237193
    Prev
    Next
    INDEX
    Explanations

    trading solutions

    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
    си
    0.57
    ad
    0.55
    anais
    0.53
    un
    0.52
    ouncil
    0.50
    verified
    0.48
    example
    0.47
    i
    0.47
    astikan
    0.46
    нус
    0.46
    POSITIVE LOGITS
    [(\
    0.45
     tray
    0.44
     儿童
    0.44
     sen
    0.42
    EY
    0.42
     cristianos
    0.42
    檐
    0.41
     trays
    0.41
     aspir
    0.41
     bán
    0.41
    Activations Density 0.000%

    No Known Activations