© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 85676
    Prev
    Next
    INDEX
    Explanations

    double or triple concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    от
    0.71
    <0xAF>
    0.64
     fără
    0.63
    ;
    0.60
     вывести
    0.56
     copi
    0.56
     ofere
    0.55
    子は
    0.55
     $(<
    0.54
    ounid
    0.54
    POSITIVE LOGITS
     double
    0.79
     Double
    0.72
    DoubleClick
    0.69
    double
    0.68
     triple
    0.66
    Double
    0.63
     duplo
    0.63
     Triple
    0.63
    triple
    0.62
     אפ
    0.57
    Activations Density 0.035%

    No Known Activations