© 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. 233488
    Prev
    Next
    INDEX
    Explanations

    March madness

    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
    났
    0.48
    yatiti
    0.47
    ack
    0.46
    ointments
    0.44
    markets
    0.43
    ---+
    0.43
     bearings
    0.42
     ارت
    0.42
    buying
    0.40
     hardening
    0.39
    POSITIVE LOGITS
     integrar
    0.61
     recorrer
    0.51
     Able
    0.50
     দুটি
    0.49
     Onc
    0.49
    ल
    0.48
     Ambiente
    0.48
     literalmente
    0.48
     Ants
    0.48
     multiplicar
    0.48
    Activations Density 0.001%

    No Known Activations