© 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. 46187
    Prev
    Next
    INDEX
    Explanations

    roman numerals for sections

    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
    ス
    1.27
    د
    1.20
    س
    1.17
    ن
    1.12
    n
    1.05
    с
    1.02
    नि
    1.00
    ку
    0.94
    あります
    0.90
    ્રી
    0.89
    POSITIVE LOGITS
    the
    1.13
     the
    0.86
    ations
    0.81
    VIII
    0.79
     IV
    0.77
     III
    0.77
    The
    0.75
    ad
    0.75
    II
    0.75
    VII
    0.75
    Activations Density 0.076%

    No Known Activations