Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 15284
    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
     skew
    1.16
     resonates
    1.12
     fluctuating
    1.11
     downside
    1.08
     emotes
    1.07
    挲
    1.06
     skewed
    1.06
     dampen
    1.06
    kada
    1.06
     boto
    1.05
    POSITIVE LOGITS
    ánh
    1.19
    찻
    1.16
     Biết
    1.11
    Я
    1.10
    Vi
    1.10
    HL
    1.09
     अंदाजा
    1.09
    Hai
    1.08
    owod
    1.08
    Fprintf
    1.08
    Activations Density 0.000%

    No Known Activations