© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 53912
    Prev
    Next
    INDEX
    Explanations

    prevent, regarding, doctor

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

    system internal creation local

    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
     fondamental
    0.50
    بط
    0.47
    lles
    0.45
     kaut
    0.44
     archaic
    0.44
     riguardo
    0.44
     trecut
    0.42
     //}
    0.42
    ناع
    0.42
     russe
    0.41
    POSITIVE LOGITS
     말씀
    0.45
    医师
    0.45
    必需
    0.44
     SUVs
    0.43
    ínt
    0.43
     jars
    0.43
     दवाओं
    0.43
     purchases
    0.43
     परिणामों
    0.43
     gallbladder
    0.43
    Activations Density 0.000%

    No Known Activations