© 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. 218291
    Prev
    Next
    INDEX
    Explanations

    record Shapiro

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

    derivative and integration constants

    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
    éb
    0.49
    ar
    0.45
    élim
    0.45
    브
    0.44
    릭
    0.44
    andex
    0.44
    albeit
    0.44
     ала
    0.44
    funciones
    0.43
    า
    0.43
    POSITIVE LOGITS
     fueling
    0.52
     pasajeros
    0.50
     scenes
    0.50
     máquinas
    0.49
     servers
    0.48
     guerras
    0.48
     fiancée
    0.48
     communists
    0.48
     guerre
    0.47
     debacle
    0.46
    Activations Density 0.001%

    No Known Activations