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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100970
    Prev
    Next
    INDEX
    Explanations

    'bout iz now knife silence

    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
    分野
    0.47
    倰
    0.42
    仍
    0.41
    商品
    0.40
    Applications
    0.40
     recovery
    0.39
     treasurer
    0.39
    マル
    0.38
    一生
    0.38
     Wastewater
    0.38
    POSITIVE LOGITS
    اعات
    0.49
     Ahab
    0.49
     эки
    0.49
     Darth
    0.49
     Jedi
    0.48
    Ĵ
    0.48
     ویژه
    0.48
     aurez
    0.47
    jaan
    0.47
     isset
    0.46
    Activations Density 0.003%

    No Known Activations