© 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. 1276
    Prev
    Next
    INDEX
    Explanations

    Python, code examples

    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
    丼
    1.21
     Delegation
    0.97
     Theories
    0.92
    planar
    0.91
     Variants
    0.91
    Course
    0.89
    Photo
    0.88
    英雄
    0.87
     PowerPoint
    0.85
    )}(
    0.85
    POSITIVE LOGITS
     asp
    1.11
    ਲ
    1.06
     ビタミン
    1.04
    umed
    1.03
    ों
    1.02
    ulas
    1.02
    朓
    1.00
     ソ
    1.00
    omme
    1.00
    फेक्ट
    0.99
    Activations Density 0.000%

    No Known Activations