© 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. 80953
    Prev
    Next
    INDEX
    Explanations

    ensuring, imply, which

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

    mimicking birds

    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
     Punk
    0.46
     Blogging
    0.45
    тена
    0.45
     Philosoph
    0.44
     Prayers
    0.44
    står
    0.43
    IANS
    0.43
    剻
    0.43
    ને
    0.43
     الدر
    0.43
    POSITIVE LOGITS
     aspectos
    0.52
    ヴォ
    0.50
     wines
    0.48
    ܬܐ
    0.48
     racionais
    0.48
     vino
    0.45
     zapewnia
    0.45
     tropics
    0.44
     navController
    0.44
     cifras
    0.44
    Activations Density 0.001%

    No Known Activations