© 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. 14142
    Prev
    Next
    INDEX
    Explanations

    Cultural Center, wildlife

    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
    मर्रा
    2.69
    sufficiency
    2.57
     Anywhere
    2.56
    DidChange
    2.50
    隍
    2.49
    sí
    2.42
    یاء
    2.39
     cliquer
    2.38
    ಲ್ಲು
    2.38
    Cpp
    2.37
    POSITIVE LOGITS
    back
    2.37
    mi
    2.36
    mrow
    2.15
    ı
    2.05
    msub
    2.05
    әм
    2.01
    izi
    1.99
    heet
    1.99
    ming
    1.98
    miy
    1.96
    Activations Density 0.007%

    No Known Activations