© 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. 704
    Prev
    Next
    INDEX
    Explanations

    SAMHSA National Helpline 1-800-662-4357

    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
    ക്കാന്‍
    0.65
     sentimos
    0.64
    zości
    0.64
    मती
    0.63
    ộp
    0.63
    movieId
    0.62
    密
    0.61
    create
    0.61
    dar
    0.61
    惨
    0.60
    POSITIVE LOGITS
    quipe
    0.70
     Today
    0.67
    叟
    0.66
     або
    0.65
     या
    0.65
    跹
    0.65
     Tomorrow
    0.65
     khúc
    0.64
     उद्या
    0.64
     ή
    0.63
    Activations Density 0.340%

    No Known Activations