© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2804
    Prev
    Next
    INDEX
    Explanations

    Natural Language Processing

    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_17_width_16k_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
    效应
    1.09
     TECHNICAL
    0.95
    age
    0.94
    penet
    0.93
    技術
    0.92
    Technical
    0.91
    然後
    0.90
    岖
    0.90
     redeemed
    0.89
    technical
    0.88
    POSITIVE LOGITS
    те
    0.78
    l
    0.77
    다고
    0.76
     occurring
    0.73
    lijke
    0.72
    __':
    0.71
    dür
    0.70
    lijk
    0.70
    lk
    0.69
    dol
    0.68
    Activations Density 0.084%

    No Known Activations