© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1536
    Prev
    Next
    INDEX
    Explanations

    trained on

    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
    rives
    0.71
    weisen
    0.71
    riving
    0.70
    大家
    0.69
    恙
    0.69
    <0xB8>
    0.68
     crook
    0.67
    described
    0.65
     commons
    0.65
    plaintext
    0.64
    POSITIVE LOGITS
    에게
    0.62
     terlalu
    0.61
    ب
    0.60
    나무
    0.60
    IMAGE
    0.59
     व्यस्त
    0.59
     آسم
    0.58
     pomiesz
    0.58
     후보
    0.57
     السماء
    0.57
    Activations Density 0.229%

    No Known Activations