© 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. 14374
    Prev
    Next
    INDEX
    Explanations

    missing or invalid values

    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
    炇
    1.89
     gxh
    1.85
    訲
    1.79
     посто
    1.72
    𝐨
    1.71
    ছনে
    1.69
    粆
    1.69
     "@/
    1.68
     維尼
    1.68
    䋇
    1.66
    POSITIVE LOGITS
    ist
    1.44
     ador
    1.40
    ある
    1.40
    istence
    1.36
    ’,
    1.36
    flare
    1.36
    ductors
    1.35
    ists
    1.34
    。「
    1.34
    at
    1.33
    Activations Density 0.044%

    No Known Activations