© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 119640
    Prev
    Next
    INDEX
    Explanations

    showing actions or states related to preceding words

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

    past tense verbs and consequences

    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
    Negative Logits
    pati
    0.48
    埼玉
    0.47
    но
    0.46
    况
    0.46
    سبب
    0.44
    的技术
    0.42
    ઈ
    0.42
    提出
    0.42
     анали
    0.41
    初步
    0.41
    POSITIVE LOGITS
     served
    0.48
     Perfecto
    0.48
     jugó
    0.47
     VERY
    0.47
     Redemption
    0.47
     bungee
    0.47
     plucked
    0.47
     देखेंगे
    0.46
     saloon
    0.46
     cursorPos
    0.46
    Activations Density 0.001%

    No Known Activations