© 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. 77474
    Prev
    Next
    INDEX
    Explanations

    profession and context

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

    note on assumptions

    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
     asks
    0.54
     profesor
    0.54
     sai
    0.52
     namanya
    0.52
     ordena
    0.48
     ask
    0.47
    ۔
    0.46
     domin
    0.46
     microphones
    0.46
     punishments
    0.46
    POSITIVE LOGITS
    عين
    0.46
     티
    0.41
    schw
    0.41
    딴
    0.40
    Total
    0.40
    Major
    0.40
     Toen
    0.40
     城
    0.40
    Device
    0.39
    renn
    0.39
    Activations Density 0.000%

    No Known Activations