© 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. 8943
    Prev
    Next
    INDEX
    Explanations

    Revision History

    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
    ১০
    1.95
    
    1.81
     instalaciones
    1.78
    }/
    1.72
    एं
    1.72
    しょ
    1.71
    ৬০
    1.71
    ৬৮
    1.69
    
    1.68
    ENABLE
    1.68
    POSITIVE LOGITS
     fancy
    1.30
    ,"
    1.28
    ."
    1.27
     yard
    1.26
    ামের
    1.24
     ."
    1.21
     decades
    1.20
     years
    1.20
    ?"
    1.20
     crowds
    1.16
    Activations Density 0.005%

    No Known Activations