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-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 4045
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     bevorzug
    0.94
    吸収
    0.94
    适
    0.93
     δημο
    0.90
    吸收
    0.90
    適
    0.88
     Angebot
    0.87
    合适
    0.86
    litt
    0.86
     適
    0.85
    POSITIVE LOGITS
     revealing
    1.42
     elucid
    1.29
     elucidate
    1.26
     reveal
    1.26
    reveal
    1.25
     elucidation
    1.24
     reconstructing
    1.17
     Reveals
    1.13
     ವಿವರ
    1.13
     insights
    1.10
    Activations Density 0.389%

    No Known Activations