© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72685
    Prev
    Next
    INDEX
    Explanations

    place names and concepts

    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
     by
    -1.02
     if
    -0.98
     Mariners
    -0.93
    AxisSize
    -0.92
    jíma
    -0.91
     της
    -0.91
    нутрен
    -0.91
    ̗
    -0.90
     planeta
    -0.90
     проводить
    -0.89
    POSITIVE LOGITS
     semejante
    1.05
     nachts
    0.96
    kość
    0.91
     possède
    0.90
     estrictamente
    0.86
     erneu
    0.86
    Външни
    0.86
    脑海
    0.86
     farmacé
    0.85
     σήμερα
    0.84
    Activations Density 0.023%

    No Known Activations