© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63571
    Prev
    Next
    INDEX
    Explanations

    check out something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Choose
    -0.94
     CHOOSE
    -0.87
     largest
    -0.87
     gewählt
    -0.82
    gry
    -0.81
    痉
    -0.81
    ואל
    -0.80
    ೦
    -0.79
    եմ
    -0.78
    andon
    -0.78
    POSITIVE LOGITS
     check
    5.38
    Check
    4.38
     Check
    4.22
    check
    4.22
     checks
    3.33
     checking
    3.30
    CHECK
    3.11
     CHECK
    3.05
    チェック
    3.00
     checkout
    2.97
    Activations Density 0.068%

    No Known Activations