© 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. 16-GEMMASCOPE-2-RES-262K
    7. 40829
    Prev
    Next
    INDEX
    Explanations

    around {pronoun}

    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_16_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
    el
    0.66
    ere
    0.64
    at
    0.64
    ้อง
    0.64
    cells
    0.63
    ം
    0.61
     U
    0.60
     N
    0.59
    ла
    0.58
     cells
    0.57
    POSITIVE LOGITS
    2
    0.76
    1
    0.69
     그는
    0.65
     purify
    0.64
     monstru
    0.63
     بابەت
    0.62
    ปี
    0.61
    7
    0.61
     thaliana
    0.60
    4
    0.60
    Activations Density 0.002%

    No Known Activations