© 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. 123020
    Prev
    Next
    INDEX
    Explanations

    story around concepts

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

    masters of, by implementing, often struggle

    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
    美國
    0.44
     snakes
    0.43
    pentine
    0.43
    Zum
    0.42
     scouring
    0.42
     сили
    0.42
    縮
    0.41
    藥
    0.41
     speeds
    0.41
    steins
    0.40
    POSITIVE LOGITS
     enjo
    0.58
     intranet
    0.54
    ')}
    0.51
     gráf
    0.50
    ර්ථ
    0.48
     ivvu
    0.48
     ovation
    0.47
    gdx
    0.47
    リズム
    0.47
     atthakath
    0.47
    Activations Density 0.000%

    No Known Activations