© 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. 13274
    Prev
    Next
    INDEX
    Explanations

    your surroundings, type of, much more

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

    types ofaction-oriented

    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
    での
    0.65
     lessened
    0.57
    有着
    0.55
     lessening
    0.54
    듦
    0.52
    想着
    0.51
    再
    0.50
     മിക
    0.49
     furthering
    0.49
     needing
    0.48
    POSITIVE LOGITS
     deshalb
    0.54
     Deshalb
    0.47
    इसलिए
    0.47
     Nevertheless
    0.46
    ischer
    0.44
    vester
    0.44
    }^{(
    0.44
     miraculously
    0.44
    ellingen
    0.43
    ්ර
    0.43
    Activations Density 0.425%

    No Known Activations