© 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. 173884
    Prev
    Next
    INDEX
    Explanations

    template file paths

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

    angular component templateUrl

    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
    ե
    0.53
    g
    0.51
     важных
    0.45
    ého
    0.45
    party
    0.44
    lanan
    0.44
    𝐞
    0.44
    lasts
    0.43
    𝐮
    0.43
    deep
    0.43
    POSITIVE LOGITS
     Salah
    0.47
     tiled
    0.46
     interfacial
    0.45
     handel
    0.45
     digitized
    0.45
     Каждый
    0.45
    "]
    0.44
     Стро
    0.44
    切れ
    0.44
     polymerized
    0.44
    Activations Density 0.000%

    No Known Activations