© 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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 987
    Prev
    Next
    INDEX
    Explanations

    African names and places

    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
     baguette
    0.26
     beetroot
    0.25
    羹
    0.25
     Significant
    0.25
    Indian
    0.25
     matcha
    0.24
    羮
    0.24
     pretzels
    0.23
    鉑
    0.23
     aromat
    0.23
    POSITIVE LOGITS
     Alhaji
    0.40
     Abia
    0.38
    ọ
    0.38
     Abuja
    0.37
     Igbo
    0.37
     Abubakar
    0.37
     Lagos
    0.36
     Ogun
    0.34
    ẹ
    0.33
     Muhammadu
    0.33
    Activations Density 0.000%

    No Known Activations