© 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. 165385
    Prev
    Next
    INDEX
    Explanations

    brazing Tube

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

    introduces contrast or exceptions

    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
     Ea
    0.52
    Variable
    0.49
     La
    0.46
     Variable
    0.45
    La
    0.44
    Пол
    0.43
    谠
    0.43
     Mutation
    0.42
     Serial
    0.42
    5
    0.42
    POSITIVE LOGITS
    initis
    0.51
     mammary
    0.50
     radiologists
    0.47
     breast
    0.46
     tuberculosis
    0.46
     pathologists
    0.46
    usta
    0.46
     tell
    0.45
     казни
    0.45
    öst
    0.45
    Activations Density 0.000%

    No Known Activations