© 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. 16-GEMMASCOPE-2-RES-262K
    4. 20815
    Prev
    Next
    INDEX
    Explanations

    kneeling

    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
    p
    0.85
    et
    0.80
    f
    0.73
    ى
    0.71
    ing
    0.70
    ри
    0.64
    eing
    0.63
    v
    0.63
    rip
    0.61
    fli
    0.60
    POSITIVE LOGITS
    B
    0.84
    İR
    0.82
    AZIONE
    0.80
     kneeling
    0.76
     moistur
    0.76
     spas
    0.75
     spices
    0.75
    মে
    0.74
     sabot
    0.74
    İM
    0.74
    Activations Density 0.001%

    No Known Activations