© 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. 65315
    Prev
    Next
    INDEX
    Explanations

    render and paint code

    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
    蛱
    -1.57
    primarily
    -1.55
    apparently
    -1.51
    originally
    -1.50
    presumably
    -1.44
    嫑
    -1.42
     konfigura
    -1.41
     😁
    -1.38
    somewhat
    -1.38
    commonly
    -1.38
    POSITIVE LOGITS
    !
    1.90
    Some
    1.75
     after
    1.67
    Despite
    1.55
    After
    1.54
    When
    1.54
    Many
    1.53
    During
    1.50
     blatantly
    1.50
     with
    1.48
    Activations Density 0.001%

    No Known Activations