© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108482
    Prev
    Next
    INDEX
    Explanations

    xml, dom, validation

    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
     trông
    -0.78
     funcionar
    -0.74
    mora
    -0.72
     Compromise
    -0.71
     없
    -0.70
     Darling
    -0.69
     Tell
    -0.68
     FRANKLIN
    -0.68
    Haar
    -0.68
     Cyl
    -0.67
    POSITIVE LOGITS
     DOM
    1.12
    DOM
    0.93
     validators
    0.83
     readers
    0.82
     dom
    0.81
     dome
    0.81
     бази
    0.79
    IBase
    0.78
     validating
    0.77
    Validators
    0.76
    Activations Density 0.039%

    No Known Activations