© 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. 46498
    Prev
    Next
    INDEX
    Explanations

    plea

    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
    a
    1.24
    o
    1.17
    n
    1.13
    in
    1.06
    to
    1.03
    其他
    1.00
    y
    0.95
    ه
    0.94
    ين
    0.93
    r
    0.92
    POSITIVE LOGITS
     plea
    1.02
     ardent
    0.89
    2
    0.88
     defam
    0.86
    ına
    0.83
     слабы
    0.83
     Plea
    0.83
    ні
    0.80
    는데
    0.79
    ։
    0.77
    Activations Density 0.001%

    No Known Activations