© 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. 234629
    Prev
    Next
    INDEX
    Explanations

    dates and party abbreviations

    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
    ỏi
    0.50
    segu
    0.49
    賈
    0.48
    態度
    0.46
    翌
    0.46
     नये
    0.46
    講
    0.46
    毅
    0.46
    發
    0.45
    ದಾರ
    0.45
    POSITIVE LOGITS
     ada
    0.52
     consisting
    0.50
     reflector
    0.48
    ্বরের
    0.48
     facility
    0.46
     connecting
    0.46
     sensor
    0.46
     linking
    0.46
     simplex
    0.46
     templ
    0.46
    Activations Density 0.000%

    No Known Activations