© 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. 41941
    Prev
    Next
    INDEX
    Explanations

    data source

    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
    ют
    0.82
    다
    0.81
    Ы
    0.79
    Ю
    0.77
    ИН
    0.76
    ИТ
    0.74
    ÕES
    0.74
     disposição
    0.73
    ك
    0.73
     electrónico
    0.73
    POSITIVE LOGITS
    '
    1.09
    1.04
    a
    0.96
    ani
    0.93
    aking
    0.91
    ag
    0.90
     is
    0.88
    ax
    0.85
     are
    0.85
    ':
    0.85
    Activations Density 0.008%

    No Known Activations