© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13945
    Prev
    Next
    INDEX
    Explanations

    urls and categories

    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_13_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
     ocup
    1.01
    ismes
    0.94
     regolare
    0.93
     régulière
    0.91
    liberal
    0.89
     специ
    0.89
     poslov
    0.89
    ヲ
    0.88
     proprement
    0.88
     assur
    0.87
    POSITIVE LOGITS
     scientists
    2.12
     researchers
    2.11
    scientists
    1.87
    Scientists
    1.79
    Researchers
    1.76
     scientist
    1.72
     nanoscale
    1.69
    科学家
    1.65
     Scientists
    1.64
     researcher
    1.63
    Activations Density 0.156%

    No Known Activations