© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 170196
    Prev
    Next
    INDEX
    Explanations

    innocent/failure/often/port contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     सरस्व
    0.55
    बंधनाच्या
    0.48
    தன்
    0.48
    ပုံ
    0.48
    ᱕
    0.48
    WORKSPACE
    0.47
    щён
    0.47
     வால்பேப்பர்கள்
    0.47
     Scrolls
    0.47
     Responsibility
    0.46
    POSITIVE LOGITS
    bia
    0.48
    ili
    0.45
    ope
    0.43
    be
    0.42
     kulture
    0.41
    िया
    0.41
    ijev
    0.41
    u
    0.41
    bari
    0.41
    जनिक
    0.41
    Activations Density 0.002%

    No Known Activations