© 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. 81371
    Prev
    Next
    INDEX
    Explanations

    lists and categories

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

    Northern Irish/Scottish

    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
     Canada
    0.46
    判
    0.46
     haunting
    0.45
    當中
    0.45
     naught
    0.44
     monumental
    0.43
    瀕
    0.43
    程式
    0.43
    權
    0.42
    保存
    0.42
    POSITIVE LOGITS
    iyasi
    0.56
    larni
    0.53
     эшлә
    0.52
    usehen
    0.49
     திருதியை
    0.48
    antikan
    0.46
    inerja
    0.46
    zter
    0.46
    ının
    0.46
    slices
    0.46
    Activations Density 0.000%

    No Known Activations