© 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. 30464
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     akhirnya
    -1.05
    ♾
    -0.92
    woordig
    -0.89
    Saber
    -0.88
     dikutip
    -0.86
    Chloroform
    -0.85
    柳
    -0.85
    летний
    -0.83
    万美元
    -0.83
     upwards
    -0.82
    POSITIVE LOGITS
     Envío
    1.13
     definido
    1.08
     Teléfono
    1.03
     adicion
    1.00
    CONCLUSIONES
    0.98
    苼
    0.98
     tejidos
    0.97
     Opiniones
    0.96
     produtos
    0.95
     Contenido
    0.94
    Activations Density 0.127%

    No Known Activations