© 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. 57648
    Prev
    Next
    INDEX
    Explanations

    places and accommodations

    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
    Dining
    -1.07
    tová
    -1.04
    :~
    -1.00
    dining
    -0.96
     dining
    -0.94
    kozások
    -0.92
    naire
    -0.88
    sted
    -0.88
     warung
    -0.86
    🤮
    -0.85
    POSITIVE LOGITS
     Entire
    1.13
     near
    0.99
     by
    0.91
     sleeps
    0.89
    便利です
    0.88
     Beautiful
    0.87
    Entire
    0.85
     among
    0.85
     Nähe
    0.82
     -
    0.81
    Activations Density 0.011%

    No Known Activations