© 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. 72149
    Prev
    Next
    INDEX
    Explanations

    virtual printer

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

    extract sensitive information

    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
    Bun
    0.43
    Coder
    0.43
    EN
    0.42
    clang
    0.42
    Á
    0.41
    BY
    0.41
     tassels
    0.41
    ๎
    0.40
    בי
    0.40
    bare
    0.40
    POSITIVE LOGITS
    dauer
    0.48
     স্মার্ট
    0.44
     ٹرسٹ
    0.44
    ડિયો
    0.44
    rekli
    0.43
    daten
    0.43
    ᱢ
    0.43
     diffic
    0.42
     राहत
    0.42
     symbiotic
    0.41
    Activations Density 0.000%

    No Known Activations