© 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. 169360
    Prev
    Next
    INDEX
    Explanations

    days of the week

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

    She saw, was, or tolerated

    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
    奋
    0.48
     dispone
    0.44
     één
    0.44
    鶉
    0.44
     فش
    0.44
     هڪ
    0.44
    出错
    0.43
     defeat
    0.43
     ç
    0.43
    <0x00>
    0.43
    POSITIVE LOGITS
    reise
    0.47
    umum
    0.46
    ger
    0.43
    tekn
    0.42
    وری
    0.42
    zon
    0.42
    tox
    0.41
     turista
    0.41
    emel
    0.41
     gib
    0.40
    Activations Density 0.001%

    No Known Activations