© 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. 1379
    Prev
    Next
    INDEX
    Explanations

    Times Square, shrimp, array, interior

    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
    漠
    1.00
    इका
    0.96
     ιδ
    0.93
    getValue
    0.91
    採用
    0.91
     valor
    0.89
    وفر
    0.89
    Les
    0.87
    s
    0.87
    erval
    0.87
    POSITIVE LOGITS
     গ্রন্থে
    1.01
     частини
    1.00
     Điện
    0.95
    吳
    0.94
    resti
    0.93
     Shame
    0.93
     darkness
    0.92
    দিনে
    0.92
    нами
    0.91
     він
    0.91
    Activations Density 0.000%

    No Known Activations