© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 14827
    Prev
    Next
    INDEX
    Explanations

    facebook ads and groups

    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_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
    虞
    0.80
    骛
    0.77
     nih
    0.75
     सांसदों
    0.74
    パンツ
    0.71
     길이가
    0.69
     needs
    0.68
    棠
    0.68
     potřeb
    0.67
     ellipso
    0.67
    POSITIVE LOGITS
    facebook
    2.16
     facebook
    2.16
     Facebook
    2.02
    Facebook
    1.95
     fb
    1.87
     फेसबुक
    1.65
     FB
    1.59
     Fb
    1.55
    fb
    1.43
    FB
    1.37
    Activations Density 0.035%

    No Known Activations