© 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. 91730
    Prev
    Next
    INDEX
    Explanations

    HTML form and UI element properties

    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
     ferons
    -0.82
    urar
    -0.82
    chromatic
    -0.76
    ulkan
    -0.75
     "));
    -0.75
    olytic
    -0.74
    રે
    -0.74
     +
    -0.73
     Kuch
    -0.72
     punggung
    -0.72
    POSITIVE LOGITS
     placeholder
    1.39
     label
    1.38
     required
    1.32
     Label
    1.14
    placeholder
    1.08
    label
    1.05
     Required
    1.05
     value
    1.05
     help
    0.97
     mandatory
    0.95
    Activations Density 0.030%

    No Known Activations