© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 281
    Prev
    Next
    INDEX
    Explanations

    process and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_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
    1.07
    u
    0.91
    e
    0.89
    ي
    0.88
    ो
    0.83
    i
    0.83
    is
    0.81
    on
    0.80
    t
    0.78
    y
    0.77
    POSITIVE LOGITS
    <unused2042>
    0.90
     all
    0.88
     جميع
    0.88
     todos
    0.82
     almost
    0.81
     છું
    0.81
     כ
    0.81
     HOW
    0.78
     وت
    0.78
     الأ
    0.78
    Activations Density 2.245%

    No Known Activations