© 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. 128891
    Prev
    Next
    INDEX
    Explanations

    friction and fuel

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

    concepts, infinities, industries

    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
    するなど
    0.51
     ט
    0.48
    ANTS
    0.48
     diferencias
    0.46
     aşağıdaki
    0.46
     дов
    0.46
     различи
    0.45
     ?
    0.45
     deserted
    0.44
     ningún
    0.44
    POSITIVE LOGITS
    fueled
    0.44
    ））
    0.44
    evaluation
    0.44
    摩擦
    0.43
    fuel
    0.43
     productService
    0.43
    which
    0.43
     UNNEEDED
    0.43
     frictional
    0.43
    capable
    0.43
    Activations Density 0.001%

    No Known Activations