© 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. 107964
    Prev
    Next
    INDEX
    Explanations

    group rate, save up, go down

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

    unique word beginnings and following phrases

    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
     专业
    0.54
     margarine
    0.48
    陶瓷
    0.47
     freien
    0.46
    基础上
    0.45
    ваць
    0.45
    盐
    0.44
    限制
    0.44
    鉐
    0.44
     آزاد
    0.44
    POSITIVE LOGITS
     <
    0.54
    uv
    0.52
    ates
    0.52
    uks
    0.51
    iki
    0.51
    uka
    0.51
    ulti
    0.51
    オク
    0.51
    imes
    0.50
    ios
    0.50
    Activations Density 0.000%

    No Known Activations