© 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. 33591
    Prev
    Next
    INDEX
    Explanations

    leadership election

    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
     so
    -1.12
     really
    -1.04
     those
    -1.02
    '>
    -0.98
    ìn
    -0.96
     היתה
    -0.94
    lė
    -0.93
     without
    -0.92
     probably
    -0.92
     actually
    -0.91
    POSITIVE LOGITS
    Template
    1.45
    <sup>
    1.44
    later
    1.20
     azonban
    1.17
    ${\
    1.17
    initi
    1.16
    .[
    1.15
     Template
    1.14
    ]],
    1.13
    还是要
    1.13
    Activations Density 0.358%

    No Known Activations