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-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 4450
    Prev
    Next
    INDEX
    Explanations

    confidential crisis support video chat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_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
     kêu
    0.80
     hospitals
    0.76
    蝠
    0.74
     ಅರ್ಜಿ
    0.74
     நாடு
    0.72
    ospitals
    0.72
     politic
    0.71
    চিক
    0.70
     зал
    0.70
     Vire
    0.70
    POSITIVE LOGITS
    izzes
    0.78
    𝐳
    0.73
     حب
    0.73
    enio
    0.72
     ModelState
    0.71
    Inner
    0.71
     simili
    0.71
    地铁
    0.70
    ığında
    0.70
     Aisha
    0.69
    Activations Density 0.092%

    No Known Activations