© 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. 13-GEMMASCOPE-2-RES-16K
    7. 1115
    Prev
    Next
    INDEX
    Explanations

    internal thought and imagination

    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_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
    器具
    1.14
     reporting
    1.03
     photometry
    1.01
    罕
    0.99
    센
    0.95
    煐
    0.95
    ได้รับ
    0.92
     назначен
    0.92
     reported
    0.91
    屽
    0.91
    POSITIVE LOGITS
    Thinking
    1.88
     thoughts
    1.86
     Thinking
    1.85
     Thoughts
    1.82
    Thoughts
    1.81
    想着
    1.80
    thoughts
    1.75
     pensamientos
    1.69
     THINK
    1.68
    thinking
    1.66
    Activations Density 1.215%

    No Known Activations