© 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. 176350
    Prev
    Next
    INDEX
    Explanations

    journal ACS

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

    declaration is

    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
     東
    0.55
    東
    0.50
     不要
    0.50
    縮
    0.50
     这是
    0.49
     当
    0.48
     สอน
    0.48
    変数
    0.47
     将
    0.47
     て
    0.47
    POSITIVE LOGITS
    সংখ্যক
    0.47
     oes
    0.43
    Lieutenant
    0.42
     synchronous
    0.42
     organised
    0.41
     keamanan
    0.41
     isinstance
    0.40
     '.';
    0.40
     assur
    0.39
    )^{*}\
    0.39
    Activations Density 0.000%

    No Known Activations