© 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. 16350
    Prev
    Next
    INDEX
    Explanations

    boolean values and operators

    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
    enswert
    -0.86
    itamos
    -0.85
    >";
    -0.82
    istir
    -0.82
    cijos
    -0.81
     anticipation
    -0.80
    mtrl
    -0.78
    ваги
    -0.77
    anwal
    -0.77
    tica
    -0.76
    POSITIVE LOGITS
    insee
    0.93
     neither
    0.91
    やや
    0.85
     tatsächlich
    0.82
     none
    0.78
     большинство
    0.78
     templado
    0.78
    を選択
    0.77
     medium
    0.77
     quase
    0.76
    Activations Density 0.075%

    No Known Activations