© 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. 14505
    Prev
    Next
    INDEX
    Explanations

    destructive thoughts, behaviors, impulses

    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
     SHO
    1.99
    哨
    1.95
    ιε
    1.92
    نيا
    1.88
    attendance
    1.83
    狎
    1.78
    ﮅ
    1.77
    ส่
    1.76
    mittance
    1.74
     филь
    1.72
    POSITIVE LOGITS
     irre
    1.57
     Brexit
    1.53
     acaso
    1.48
    irre
    1.43
    COME
    1.36
     refreshing
    1.35
     ligation
    1.33
     irrevers
    1.32
     irrevocable
    1.31
     dredge
    1.31
    Activations Density 0.045%

    No Known Activations