© 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. 31-GEMMASCOPE-2-RES-262K
    7. 29776
    Prev
    Next
    INDEX
    Explanations

    pre-installed software

    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
     পিটার
    0.52
    矵
    0.49
    䂘
    0.48
     Ian
    0.45
     iPads
    0.44
    蛜
    0.44
     landlab
    0.44
    Ger
    0.43
    喍
    0.43
    Paul
    0.42
    POSITIVE LOGITS
     Xiaomi
    0.65
     Redmi
    0.60
     Huawei
    0.59
     MIUI
    0.59
     الصين
    0.59
    Huawei
    0.57
     HUAWEI
    0.54
     Chinese
    0.54
     चीन
    0.53
     OnePlus
    0.53
    Activations Density 0.054%

    No Known Activations