© 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. 210297
    Prev
    Next
    INDEX
    Explanations

    Northern Europe, inside out

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

    efficiency and problems

    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
    Conflicts
    0.50
    Dataset
    0.49
     губерна
    0.48
     пове
    0.47
    moid
    0.47
    يره
    0.47
     オーバー
    0.47
    ]("
    0.47
     festgelegt
    0.47
     überprüft
    0.47
    POSITIVE LOGITS
     Michael
    0.47
     Brian
    0.46
    ेष
    0.45
     macrom
    0.44
    ɧ
    0.44
    ⇩
    0.43
    nings
    0.42
     Ramos
    0.42
     ky
    0.42
     gla
    0.42
    Activations Density 0.000%

    No Known Activations