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. 4021
    Prev
    Next
    INDEX
    Explanations

    threatens or abuses children

    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
     izquierdo
    0.78
    LEFT
    0.75
     capucha
    0.74
     मारा
    0.74
    left
    0.72
    ortheast
    0.72
    izquierda
    0.70
    ᛁ
    0.69
    ObjectType
    0.69
    ács
    0.69
    POSITIVE LOGITS
     treat
    0.77
     expose
    0.67
     बोले
    0.65
     Treat
    0.62
     tratti
    0.62
    Bsky
    0.62
    곡
    0.61
     specialize
    0.61
     Presentation
    0.61
    шем
    0.60
    Activations Density 0.012%

    No Known Activations