© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 139355
    Prev
    Next
    INDEX
    Explanations

    when followed by a noun/pronoun

    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
     revelation
    0.43
     Tragedy
    0.41
     Democracy
    0.40
    綎
    0.40
    ాన్
    0.39
     చేస్తున్నారు
    0.39
     Donna
    0.38
    гой
    0.38
     హైదర్
    0.38
     విభ
    0.38
    POSITIVE LOGITS
    เมื่อ
    0.59
    Ş
    0.59
    Когда
    0.57
    cuando
    0.55
    В
    0.53
    Cuando
    0.50
    A
    0.50
    Quando
    0.50
    К
    0.50
    Раз
    0.49
    Activations Density 0.009%

    No Known Activations