© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75673
    Prev
    Next
    INDEX
    Explanations

    C-2, K-4, two

    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
    न्दु
    -0.77
    DropTable
    -0.75
     reading
    -0.75
     nervous
    -0.74
    rees
    -0.74
     parati
    -0.72
     Playhouse
    -0.72
    四
    -0.71
    queline
    -0.71
     Consolidated
    -0.71
    POSITIVE LOGITS
    <0xA2>
    0.75
     deux
    0.73
    Preliminaries
    0.72
    Rodney
    0.71
     двумя
    0.70
    ດ
    0.70
    ño
    0.70
     двух
    0.69
     cheated
    0.68
    Two
    0.68
    Activations Density 0.089%

    No Known Activations