© 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. 225658
    Prev
    Next
    INDEX
    Explanations

    travel disruptions

    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
     當
    0.52
    OCATION
    0.46
    ный
    0.45
     सब्जी
    0.44
    星
    0.44
     來
    0.44
     BTW
    0.42
    底
    0.42
    চ্যুত
    0.42
     சங்க
    0.42
    POSITIVE LOGITS
     even
    0.45
     sequences
    0.44
     indicators
    0.44
     hashtags
    0.44
     horrors
    0.43
     frumo
    0.43
     doubts
    0.42
    iPad
    0.42
    errated
    0.42
     Sequences
    0.42
    Activations Density 0.001%

    No Known Activations