© 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. 49661
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
     had
    -0.80
     many
    -0.79
     prolonged
    -0.79
     requires
    -0.78
     removes
    -0.76
     hundreds
    -0.75
     classy
    -0.75
    してくれた
    -0.74
     Quite
    -0.74
     dozens
    -0.74
    POSITIVE LOGITS
     الرج
    0.79
     trich
    0.78
    islav
    0.77
     optics
    0.77
     synt
    0.76
     VJ
    0.76
     Tk
    0.75
    <tfoot>
    0.75
     apri
    0.75
    Minutes
    0.75
    Activations Density 0.003%

    No Known Activations