© 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. 22511
    Prev
    Next
    INDEX
    Explanations

    numbers and currency amounts

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

    currency amounts and conversions

    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
    堭
    0.43
    aways
    0.40
    blackberry
    0.40
     величе
    0.40
    зів
    0.39
     informasjon
    0.39
     ৩৮
    0.39
     adhere
    0.38
     claridad
    0.38
    িসের
    0.38
    POSITIVE LOGITS
     <<
    0.42
     posts
    0.42
     Neutron
    0.41
     Oste
    0.41
     parte
    0.41
    [
    0.40
    <strong>
    0.40
     Eth
    0.39
    .。
    0.39
     Neut
    0.39
    Activations Density 0.000%

    No Known Activations