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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78780
    Prev
    Next
    INDEX
    Explanations

    iostream, endl

    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
    aini
    -0.85
    фере
    -0.85
    writeInt
    -0.84
     Finale
    -0.82
    bleau
    -0.81
    теря
    -0.79
     نکته
    -0.78
    TextBlock
    -0.77
     erhält
    -0.75
     IActionResult
    -0.75
    POSITIVE LOGITS
    endl
    1.55
     endl
    1.16
    喹
    0.90
     "}";
    0.87
    ведення
    0.86
    〛
    0.85
    Длина
    0.77
    utilizzo
    0.77
     активно
    0.77
    gucci
    0.77
    Activations Density 0.002%

    No Known Activations