© 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. 109256
    Prev
    Next
    INDEX
    Explanations

    academic essays and reviews

    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
    Ін
    -0.84
    ↞
    -0.79
    記者
    -0.77
    Prensa
    -0.77
    cdot
    -0.76
    Reuters
    -0.76
    Истори
    -0.75
     zufried
    -0.74
     termurah
    -0.72
     Moffat
    -0.71
    POSITIVE LOGITS
     symposium
    1.12
     essays
    1.08
     essay
    0.99
    sym
    0.93
     forum
    0.85
    Essay
    0.84
    entretien
    0.83
     SYMP
    0.83
     ej
    0.83
     entretien
    0.82
    Activations Density 0.049%

    No Known Activations