© 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. 182787
    Prev
    Next
    INDEX
    Explanations

    World record Largest Serving

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

    vehicle portrayed sexually

    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
    💬
    0.52
     metade
    0.49
     més
    0.46
     direcion
    0.46
    言
    0.45
     híbr
    0.45
     intermédiaire
    0.45
     chien
    0.45
     più
    0.44
     mettre
    0.44
    POSITIVE LOGITS
     đất
    0.52
     Railroad
    0.47
     Potatoes
    0.47
     Growers
    0.47
    Washington
    0.46
    agonal
    0.46
     =-\
    0.46
    India
    0.45
    Maharashtra
    0.45
    assignments
    0.44
    Activations Density 0.000%

    No Known Activations