© 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. 17-GEMMASCOPE-2-RES-16K
    7. 550
    Prev
    Next
    INDEX
    Explanations

    subtle physical actions and expressions

    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_17_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
     (\
    1.62
    (\
    1.46
    ^{*}(\
    1.37
     ব্যক্তিদের
    1.37
    享有
    1.35
     প্রতিষ্ঠান
    1.34
    }({\
    1.33
    ^{(\
    1.33
     (%
    1.29
    器件
    1.29
    POSITIVE LOGITS
     smirk
    2.01
     angrily
    1.88
     muttered
    1.87
     trembling
    1.86
     nervously
    1.85
     glanced
    1.83
     softly
    1.80
     mumbled
    1.79
     hurriedly
    1.78
     glances
    1.78
    Activations Density 1.311%

    No Known Activations