© 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. 34-GEMMASCOPE-RES-131K
    7. 30586
    Prev
    Next
    INDEX
    Explanations

    you can also

    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
     probably
    -1.25
     perhaps
    -1.10
     likely
    -1.03
     possibly
    -0.97
     maybe
    -0.96
     first
    -0.96
     could
    -0.96
    謄
    -0.91
     probablemente
    -0.88
     might
    -0.87
    POSITIVE LOGITS
     belieb
    1.25
     любой
    1.18
     любого
    1.16
     dowol
    1.11
    有任何
    1.09
     freely
    1.02
     навыки
    1.02
    有多
    1.00
     cualquier
    1.00
     multiple
    1.00
    Activations Density 0.130%

    No Known Activations