© 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. 110826
    Prev
    Next
    INDEX
    Explanations

    later developed

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

    generate, identified, mechanism, brain

    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
    學者
    0.43
     fentanyl
    0.42
    雋
    0.42
    ሼ
    0.42
     iodide
    0.41
     मानते
    0.41
     студентов
    0.41
    ծ
    0.41
     SCREEN
    0.41
     arson
    0.41
    POSITIVE LOGITS
    native
    0.49
     trava
    0.49
     gön
    0.47
     closeness
    0.44
     来自
    0.43
     少し
    0.43
     spraw
    0.43
     তহ
    0.43
     tah
    0.42
     Сьогодні
    0.42
    Activations Density 0.001%

    No Known Activations