© 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. 27406
    Prev
    Next
    INDEX
    Explanations

    the name Mary

    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
    ע
    1.46
    ל
    1.33
    מ
    1.32
    ח
    1.30
    ك
    1.23
    ن
    1.18
    ل
    1.15
     I
    1.13
    ur
    1.09
    מח
    1.09
    POSITIVE LOGITS
    s
    2.81
    ים
    1.91
    ی
    1.86
    ς
    1.70
    ের
    1.61
    های
    1.42
    ą
    1.38
    ओं
    1.35
    ות
    1.32
    いる
    1.30
    Activations Density 0.001%

    No Known Activations