© 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. 106209
    Prev
    Next
    INDEX
    Explanations

    money or price

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

    lead to

    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
     LPTMR
    0.54
    கன்
    0.49
     "["
    0.49
    🧉
    0.47
    ༡
    0.44
     distinguishers
    0.44
     заявление
    0.44
     allegation
    0.43
     labile
    0.43
     ["[
    0.42
    POSITIVE LOGITS
    e
    0.56
    off
    0.55
    or
    0.50
    of
    0.50
    price
    0.48
    om
    0.48
    als
    0.48
    ell
    0.47
    (
    0.47
    wie
    0.47
    Activations Density 0.000%

    No Known Activations