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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8744
    Prev
    Next
    INDEX
    Explanations

    take seriously or lightly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kimberley
    0.95
     rede
    0.95
     McLeod
    0.86
     Cheapest
    0.83
    avay
    0.82
    Sud
    0.82
    ণিত
    0.81
    결
    0.81
    aud
    0.81
     Khanna
    0.80
    POSITIVE LOGITS
    serious
    2.19
     serious
    2.10
    Serious
    1.94
     seriously
    1.93
     Serious
    1.88
     seriousness
    1.84
     serius
    1.81
    seriously
    1.72
     sérieux
    1.67
     serio
    1.63
    Activations Density 0.154%

    No Known Activations