© 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. 76696
    Prev
    Next
    INDEX
    Explanations

    related conjunctions and explanations

    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
    ل
    0.62
    ن
    0.60
    ك
    0.59
    ountains
    0.50
    ت
    0.49
    ي
    0.46
    一
    0.44
    姓
    0.43
    ط
    0.43
    水
    0.43
    POSITIVE LOGITS
    jä
    0.50
     apabila
    0.49
     μεταξύ
    0.49
    VING
    0.49
     mengenai
    0.47
    關於
    0.47
     ἢ
    0.47
     Concerning
    0.44
     concerning
    0.44
     సంబంధించిన
    0.44
    Activations Density 0.001%

    No Known Activations