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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 11172
    Prev
    Next
    INDEX
    Explanations

    joke, combination, how it

    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_16_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
     in
    0.59
     adopt
    0.54
    ,
    0.54
     officials
    0.49
     reporters
    0.49
     journalists
    0.47
     Polaris
    0.47
     enquiries
    0.46
    ”.
    0.46
     observers
    0.46
    POSITIVE LOGITS
    ล
    0.51
    音
    0.51
     دینا
    0.50
     رنگ
    0.50
     گیا
    0.48
    ป่วย
    0.47
    iped
    0.47
     क्षार
    0.47
    [])
    0.46
     सैलरी
    0.46
    Activations Density 0.000%

    No Known Activations