© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75722
    Prev
    Next
    INDEX
    Explanations

    tennis tournaments and rankings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Иск
    -0.86
     septic
    -0.73
    Наде
    -0.72
     Atta
    -0.72
     Atwood
    -0.71
    読む
    -0.71
     Aha
    -0.71
     saper
    -0.70
    webapp
    -0.69
    Недо
    -0.68
    POSITIVE LOGITS
    __('
    0.80
     Earth
    0.77
    _),
    0.72
    ̦
    0.71
    ampling
    0.71
    AppCompatTheme
    0.71
     MessageType
    0.71
    cue
    0.71
     😭😭
    0.70
     JJ
    0.68
    Activations Density 0.037%

    No Known Activations