© 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. 22-GEMMASCOPE-RES-131K
    7. 39226
    Prev
    Next
    INDEX
    Explanations

    object attribute initialization

    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
     from
    -1.25
     then
    -0.98
    tır
    -0.94
     before
    -0.92
     таке
    -0.89
    ->___
    -0.89
     during
    -0.88
    其
    -0.87
    つく
    -0.86
    ení
    -0.86
    POSITIVE LOGITS
     gewissen
    1.04
    ⇘
    0.99
    Nieuwe
    0.98
    卺
    0.95
     applau
    0.94
     fondament
    0.93
    Inhoud
    0.91
     conç
    0.90
    hält
    0.90
     crée
    0.90
    Activations Density 0.015%

    No Known Activations