© 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. 112416
    Prev
    Next
    INDEX
    Explanations

    historical documents and information

    np_acts-logits-general · gemini-2.5-flash-lite

    runtime performance or filtering inappropriateness

    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
     milhares
    0.55
     você
    0.51
     comunidades
    0.49
     policía
    0.48
     soyez
    0.47
     iniciando
    0.45
     educación
    0.45
    剷
    0.45
     acredita
    0.44
     policías
    0.44
    POSITIVE LOGITS
     Treatise
    0.54
     Text
    0.52
     Dictionary
    0.48
     Comparative
    0.48
    ের
    0.47
     इक्वेशन
    0.47
     Vintage
    0.46
    原来的
    0.46
     Historical
    0.46
     antiquated
    0.46
    Activations Density 0.001%

    No Known Activations