© 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. 49581
    Prev
    Next
    INDEX
    Explanations

    Reversal, Manifesto

    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
     Kilometer
    -0.76
    Redacción
    -0.75
    テンツ
    -0.75
    ytte
    -0.75
    uelos
    -0.71
    oneofs
    -0.70
     gulp
    -0.69
    ainville
    -0.69
    펫
    -0.69
    zda
    -0.68
    POSITIVE LOGITS
     ALLE
    0.85
    ALLE
    0.80
    alleg
    0.76
     almend
    0.75
     woven
    0.74
    Һ
    0.72
     Allegro
    0.71
     Príncipe
    0.70
    mRNA
    0.70
    usted
    0.70
    Activations Density 0.006%

    No Known Activations