© 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. 241505
    Prev
    Next
    INDEX
    Explanations

    Foreign language or specific phrases

    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
     životu
    0.58
     〔
    0.55
     そこ
    0.52
    Ⅳ
    0.52
     キッズ
    0.51
     フ
    0.50
     開
    0.49
     そう
    0.48
     ロー
    0.48
    ArchiveAction
    0.48
    POSITIVE LOGITS
    的最
    0.43
     असू
    0.42
     selon
    0.41
     cuales
    0.41
     ab
    0.39
     sujetos
    0.38
     Alien
    0.38
     rę
    0.38
     del
    0.38
    سین
    0.38
    Activations Density 0.001%

    No Known Activations