© 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. 59418
    Prev
    Next
    INDEX
    Explanations

    legal topics or code snippets

    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
     både
    -0.96
     both
    -0.85
     Tienen
    -0.85
     atmosf
    -0.85
     Woche
    -0.85
     Sachen
    -0.84
    Endian
    -0.84
     cabecera
    -0.84
    opold
    -0.82
    ==$
    -0.82
    POSITIVE LOGITS
    uppe
    0.88
    それだけ
    0.86
     new
    0.86
     fals
    0.83
     was
    0.82
    BETH
    0.82
    niająca
    0.79
    SUGGEST
    0.78
     Likewise
    0.78
    ença
    0.78
    Activations Density 0.003%

    No Known Activations