Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 2730
    Prev
    Next
    INDEX
    Explanations

    network concepts and terms

    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
    hipping
    1.04
    వులు
    0.92
    ushu
    0.89
    phoneNumber
    0.88
     laboral
    0.88
     브랜드
    0.88
     */}
    0.85
     مشینیں
    0.84
    檯
    0.83
     داله
    0.83
    POSITIVE LOGITS
    ed
    1.06
    ect
    0.90
    状况
    0.88
     topography
    0.86
     lưới
    0.85
    ron
    0.85
    shakes
    0.84
    raster
    0.81
     congestion
    0.81
    கா
    0.80
    Activations Density 0.114%

    No Known Activations