© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 157220
    Prev
    Next
    INDEX
    Explanations

    phpFreeChat

    np_acts-logits-general · gemini-2.5-flash-lite

    travel passes and city cards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ก็
    0.55
    隱
    0.52
    别
    0.49
    隐
    0.48
    गो
    0.47
    隠
    0.47
    绝
    0.47
    现在
    0.47
    京
    0.47
    万
    0.46
    POSITIVE LOGITS
     automakers
    0.60
     automaker
    0.53
     deteriorating
    0.51
     policymakers
    0.49
     sculptor
    0.49
     Allgemeinen
    0.49
     national
    0.48
    ífica
    0.48
     manufacturers
    0.48
     schoolchildren
    0.48
    Activations Density 0.000%

    No Known Activations