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. 40-GEMMASCOPE-2-RES-262K
    4. 5823
    Prev
    Next
    INDEX
    Explanations

    gift of, gift card, gift subscription

    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_40_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
    魎
    0.42
    ütter
    0.42
    legant
    0.40
    魉
    0.40
    ologische
    0.38
    rolog
    0.38
     Foundry
    0.37
     urinary
    0.37
    Touchable
    0.37
    dml
    0.37
    POSITIVE LOGITS
     gift
    0.84
    Gift
    0.82
    🎁
    0.82
     gifts
    0.77
     Gift
    0.76
     tặng
    0.76
    gift
    0.73
    赠
    0.69
     GIFT
    0.67
    贈
    0.67
    Activations Density 0.003%

    No Known Activations