Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 39011
    Prev
    Next
    INDEX
    Explanations

    tens column or header

    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
    洋
    0.49
    CompoundButton
    0.47
    د
    0.47
    ประก
    0.46
    сно
    0.45
     acond
    0.44
     кон
    0.43
    д
    0.43
     règles
    0.42
    год
    0.42
    POSITIVE LOGITS
    ns
    0.46
     नारेबाजी
    0.43
    otti
    0.42
     Fleming
    0.41
    owness
    0.41
    ociaż
    0.41
     NS
    0.41
     Armstrong
    0.41
    考える
    0.41
    uacute
    0.41
    Activations Density 0.002%

    No Known Activations