© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 192942
    Prev
    Next
    INDEX
    Explanations

    from the productions

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

    harmful advice or actions

    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
    Negative Logits
     didn
    0.46
     perdere
    0.46
     মাথায়
    0.44
     scrivere
    0.44
     iniziare
    0.43
    悩
    0.43
     disables
    0.43
     শ্রেণীর
    0.43
     stared
    0.42
     coincided
    0.42
    POSITIVE LOGITS
    ت
    0.56
    رخ
    0.54
    ذر
    0.53
    报警
    0.53
    است
    0.50
     Rooms
    0.50
    یت
    0.49
    áték
    0.49
    epik
    0.48
    枺
    0.48
    Activations Density 0.002%

    No Known Activations