© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 45055
    Prev
    Next
    INDEX
    Explanations

    spurs and spurred

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     través
    1.95
    们
    1.91
    నూ
    1.88
    わからない
    1.86
    们的
    1.83
    보니
    1.74
    보면
    1.73
    지
    1.71
    骈
    1.69
    m
    1.65
    POSITIVE LOGITS
    ल
    2.03
    n
    1.69
    utives
    1.54
    го
    1.52
    mage
    1.48
    bangan
    1.48
     spurs
    1.45
    rue
    1.43
     Hotspur
    1.42
    wink
    1.41
    Activations Density 0.001%

    No Known Activations