© 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. 1913
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis after specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     leverages
    1.56
     savvy
    1.50
     leverage
    1.47
     leveraging
    1.44
     stakeholders
    1.43
     clueless
    1.39
    savvy
    1.37
    仼
    1.35
     getNodeId
    1.35
     KPIs
    1.34
    POSITIVE LOGITS
     vols
    1.43
     compiled
    1.29
     Vols
    1.24
     occasioned
    1.19
     Compiled
    1.15
     reprint
    1.14
     chiefly
    1.12
    cellaneous
    1.11
     series
    1.11
    .]
    1.10
    Activations Density 0.315%

    No Known Activations