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. 3641
    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
     שה
    1.65
    ו
    1.59
     ש
    1.56
     That
    1.51
     ל
    1.50
     ב
    1.49
     ט
    1.47
     ה
    1.45
     בש
    1.44
     that
    1.42
    POSITIVE LOGITS
    லாமல்
    1.55
     temprano
    1.45
    𝚒
    1.43
    𝚞
    1.36
     jeweil
    1.34
    ében
    1.33
    পন্ন
    1.33
     jeweiligen
    1.31
    besondere
    1.31
     gonflement
    1.30
    Activations Density 0.010%

    No Known Activations