© 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. 72794
    Prev
    Next
    INDEX
    Explanations

    free productssuperior products

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

    code or build targets

    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
    <unused506>
    0.32
     bhavati
    0.32
    jay
    0.32
     ficha
    0.31
     ଭ
    0.31
    isine
    0.31
    hindi
    0.31
    ፑ
    0.31
     রহমান
    0.30
    ositol
    0.30
    POSITIVE LOGITS
     However
    0.34
     trotzdem
    0.34
     But
    0.33
     البته
    0.33
    还得
    0.32
     المهم
    0.32
    🙀
    0.32
     сцен
    0.31
     يقوم
    0.31
     மறந்து
    0.31
    Activations Density 0.067%

    No Known Activations