© 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. 7-GEMMASCOPE-2-RES-16K
    7. 397
    Prev
    Next
    INDEX
    Explanations

    collecting feedback

    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_7_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
    \'
    0.99
    怕
    0.96
     !_
    0.94
    InputChange
    0.94
    MappingURL
    0.93
    ೇವಿನ
    0.93
    HUB
    0.92
    Mua
    0.91
    И
    0.90
     ماشي
    0.90
    POSITIVE LOGITS
     Moreover
    1.02
     Fortunately
    0.95
     Furthermore
    0.93
     Interestingly
    0.92
     Consequently
    0.91
     Unfortunately
    0.91
     Despite
    0.87
     Indeed
    0.86
     Similarly
    0.86
     Nevertheless
    0.84
    Activations Density 0.000%

    No Known Activations