© 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. 146690
    Prev
    Next
    INDEX
    Explanations

    states or abbreviations

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

    conversational / formal styles

    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
    anej
    0.42
    install
    0.42
    >=
    0.41
     mappings
    0.41
    harga
    0.41
     investimentos
    0.41
     Physica
    0.40
     >=
    0.40
    льною
    0.40
    itatively
    0.40
    POSITIVE LOGITS
     наста
    0.44
     evokes
    0.43
    diocese
    0.43
     сми
    0.43
     الاعت
    0.42
     نب
    0.40
    วล
    0.39
    籁
    0.39
    amerika
    0.39
     ہوا۔
    0.38
    Activations Density 0.000%

    No Known Activations