© 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. 32306
    Prev
    Next
    INDEX
    Explanations

    a certain phrase

    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
     heretofore
    -1.09
     eminently
    -1.04
     hitherto
    -1.01
     asseg
    -0.98
     putative
    -0.95
     ostensibly
    -0.92
     erst
    -0.90
     confirming
    -0.85
     refinements
    -0.85
    因而
    -0.85
    POSITIVE LOGITS
    すごく
    1.09
    řské
    1.08
    (!__
    1.06
     gemeenten
    1.03
     inwoners
    0.98
    accharides
    0.97
     damaligen
    0.97
    atzes
    0.95
    ybė
    0.95
     огром
    0.94
    Activations Density 0.081%

    No Known Activations