© 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. 199693
    Prev
    Next
    INDEX
    Explanations

    foreign scripts and specific terms

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

    witnessed liberalization

    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
    ms
    0.52
    hol
    0.52
    mt
    0.48
    es
    0.47
     Android
    0.47
    isa
    0.47
    isierung
    0.46
    s
    0.46
     studi
    0.46
     comunic
    0.46
    POSITIVE LOGITS
    лянчук
    0.50
    вард
    0.49
    頌
    0.49
     Opfer
    0.49
    йн
    0.48
     Вар
    0.48
    ᠶ
    0.48
     оши
    0.48
     дві
    0.48
    ㄶ
    0.47
    Activations Density 0.001%

    No Known Activations