© 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. 484
    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
    还是很
    1.26
    很是
    1.22
    꽤
    1.20
     somewhat
    1.16
     obviously
    1.16
     Apparently
    1.14
     evidently
    1.14
    頗
    1.13
     khá
    1.13
     상당히
    1.13
    POSITIVE LOGITS
     underestimate
    1.26
     anyone
    1.24
    Anything
    1.16
     anybody
    1.16
    anyone
    1.13
     any
    1.11
     complacency
    1.10
     qualquer
    1.09
     EVER
    1.09
     ANY
    1.07
    Activations Density 1.880%

    No Known Activations