© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69944
    Prev
    Next
    INDEX
    Explanations

    patient demographics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_width_262k_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
     incarcerated
    1.65
    患
    1.54
    treatment
    1.54
    treated
    1.47
    Treatment
    1.47
    parat
    1.45
     cận
    1.42
     harmed
    1.40
    боли
    1.39
    )^{[\
    1.39
    POSITIVE LOGITS
     mais
    1.57
    插件
    1.55
    ology
    1.53
     Manuel
    1.52
     fonts
    1.51
     Google
    1.51
     linguistics
    1.48
    会自动
    1.43
    Google
    1.43
     referee
    1.42
    Activations Density 0.001%

    No Known Activations