© 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. 2659
    Prev
    Next
    INDEX
    Explanations

    Filing Status, evaluation of, Economic Outlook, More Notes

    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
     where
    -0.93
     специаль
    -0.79
    ನ್ನ
    -0.77
     ню
    -0.76
    ocarpus
    -0.76
    擎
    -0.75
     so
    -0.73
    tese
    -0.72
     may
    -0.71
    ھر
    -0.71
    POSITIVE LOGITS
     keineswegs
    1.06
     ,.
    1.05
     fervent
    0.96
     (,
    0.94
     energi
    0.93
     детского
    0.93
    ¡¡
    0.92
    ñora
    0.92
     …..
    0.91
    })
    0.89
    Activations Density 0.003%

    No Known Activations