© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4672
    Prev
    Next
    INDEX
    Explanations

    founder or chairman

    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_22_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
    她们
    0.75
     прока
    0.74
    它們
    0.73
     obey
    0.71
    它们
    0.70
    helpers
    0.70
     ಅವು
    0.70
    삐
    0.69
    oby
    0.68
    picks
    0.68
    POSITIVE LOGITS
     founder
    1.03
    founder
    0.96
    Founder
    0.90
     Founder
    0.89
     figure
    0.86
     fondateur
    0.85
     chairman
    0.85
     founding
    0.82
     Chairman
    0.82
    Chairman
    0.82
    Activations Density 0.393%

    No Known Activations