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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 196
    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_17_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
     краса
    0.96
     offrant
    0.88
     offrir
    0.86
     Offering
    0.85
    ()));
    0.85
    那样
    0.84
     offrent
    0.83
     выпуска
    0.83
    つもり
    0.83
    "));
    0.81
    POSITIVE LOGITS
     attributable
    2.26
     caused
    2.09
    caused
    2.07
     disebabkan
    2.06
     stemming
    2.05
     related
    2.00
    related
    1.91
     arising
    1.91
     связано
    1.91
     stemmed
    1.88
    Activations Density 3.446%

    No Known Activations