© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 141141
    Prev
    Next
    INDEX
    Explanations

    fees and programs

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

    convolutional neural networks

    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
    Negative Logits
    የር
    0.49
    wens
    0.48
    အတွ
    0.48
    範
    0.48
    tissue
    0.46
    i
    0.46
    ut
    0.44
    γω
    0.43
    丝
    0.43
     calendriers
    0.43
    POSITIVE LOGITS
     kiló
    0.44
     Bla
    0.44
     hydroxy
    0.43
     clásico
    0.43
     Schle
    0.42
     Rami
    0.42
     chapel
    0.41
    стави
    0.41
     siku
    0.41
     pancake
    0.40
    Activations Density 0.000%

    No Known Activations