© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15142
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     ብዙውን
    0.65
     ജന
    0.62
    ប្រភេទ
    0.61
     സ്ത്ര
    0.61
    軖
    0.60
    ஆம்
    0.58
    
    0.56
     এছাড়াও
    0.55
    សូម
    0.55
     금액
    0.55
    POSITIVE LOGITS
     θ
    1.66
     ρ
    1.59
     ϕ
    1.59
     ∂
    1.57
     λ
    1.56
     <
    1.49
     σ
    1.49
     τ
    1.48
     ƒ
    1.47
     φ
    1.45
    Activations Density 0.129%

    No Known Activations