© 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. 208
    Prev
    Next
    INDEX
    Explanations

    object-oriented programming concepts

    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
     virtually
    1.08
     lasting
    0.98
     shot
    0.97
     ‘
    0.97
     –
    0.96
     legitimately
    0.96
     ’
    0.95
     soon
    0.93
    ↵
    0.92
     bound
    0.91
    POSITIVE LOGITS
        
    1.70
    Если
    1.67
    <!--
    1.59
    Selain
    1.58
                            
    1.58
    此外
    1.57
            
    1.55
    Ко
    1.55
    1.55
    Setelah
    1.54
    Activations Density 0.149%

    No Known Activations