© 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. 22-GEMMASCOPE-RES-131K
    7. 34383
    Prev
    Next
    INDEX
    Explanations

    opposition, runner, quarterfinals

    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_22/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
     when
    -1.32
     provided
    -1.02
     Retired
    -1.01
     defined
    -0.99
     When
    -0.98
     (
    -0.97
     когда
    -0.97
    :
    -0.97
     specific
    -0.96
     specified
    -0.96
    POSITIVE LOGITS
     beaucoup
    1.16
    eſ
    1.04
     others
    1.02
     masih
    1.02
    θεση
    1.00
     alcuni
    0.99
    ᡴ
    0.98
    ᨈ
    0.98
    Tämä
    0.97
     餐厅
    0.97
    Activations Density 0.012%

    No Known Activations