© 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. 123489
    Prev
    Next
    INDEX
    Explanations

    European official publication

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

    magic, sacred, punctuation

    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
    🔛
    0.56
    ​)
    0.55
    💚
    0.51
    RestController
    0.51
    ())
    0.48
    ’)
    0.48
    ”)
    0.46
    ...");
    0.45
     కరో
    0.45
    opio
    0.45
    POSITIVE LOGITS
     publi
    0.51
     officielle
    0.48
     rdf
    0.46
     الأولى
    0.45
     publie
    0.45
     entrer
    0.44
     internationale
    0.43
     لام
    0.43
     officielles
    0.43
     arth
    0.43
    Activations Density 0.000%

    No Known Activations