© 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. 40-GEMMASCOPE-2-RES-262K
    7. 20749
    Prev
    Next
    INDEX
    Explanations

    contrasting or additive comparisons

    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
    П
    0.33
    Μ
    0.33
    ُ
    0.31
    5
    0.30
    รู
    0.30
     pierwsze
    0.30
    특히
    0.30
    <0xE7>
    0.30
    Ν
    0.30
    ノール
    0.29
    POSITIVE LOGITS
     hingegen
    0.65
    こちらは
    0.64
     ebenfalls
    0.61
    こちらも
    0.57
     natomiast
    0.54
     Conversely
    0.51
     likewise
    0.50
    វិញ
    0.50
    Conversely
    0.50
     こちら
    0.50
    Activations Density 0.113%

    No Known Activations