© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 246152
    Prev
    Next
    INDEX
    Explanations

    connect / connection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    चुरी
    0.55
    箩
    0.54
     вероятно
    0.47
    表现
    0.45
    ાસ
    0.45
    ลม
    0.44
    <0x9E>
    0.44
    永
    0.44
    Β
    0.44
    ুর
    0.43
    POSITIVE LOGITS
     conectar
    0.50
     conexión
    0.49
     mittlerweile
    0.49
     połą
    0.47
     připoj
    0.45
     poda
    0.44
     conect
    0.43
     conexão
    0.43
     plugin
    0.43
    ंसाठी
    0.43
    Activations Density 0.000%

    No Known Activations