© 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. 211592
    Prev
    Next
    INDEX
    Explanations

    non-english characters

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

    capital, captain, caption

    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
    ol
    0.57
    ur
    0.55
    ><
    0.55
    im
    0.51
    Chemical
    0.50
     worldRank
    0.49
    <h1>
    0.48
    Scientific
    0.48
     смесь
    0.48
    es
    0.48
    POSITIVE LOGITS
    ومان
    0.51
     جوړونکو
    0.51
    قی
    0.49
    كام
    0.47
    菩
    0.46
    вена
    0.46
    мпа
    0.45
    ິນ
    0.45
    ومین
    0.45
    مین
    0.44
    Activations Density 0.000%

    No Known Activations