© 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. 9113
    Prev
    Next
    INDEX
    Explanations

    P followed by specific characters or word parts

    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
    2.17
    i
    1.74
    y
    1.72
    e
    1.48
    as
    1.45
    t
    1.45
    g
    1.39
    b
    1.38
    an
    1.36
    and
    1.35
    POSITIVE LOGITS
    大
    1.15
    ка
    1.12
    ляется
    1.02
     осуществ
    1.02
    人
    1.01
    FileInputExcel
    0.99
    ד
    0.98
    ι
    0.96
    大海
    0.95
    ุ
    0.94
    Activations Density 0.541%

    No Known Activations