© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1443
    Prev
    Next
    INDEX
    Explanations

    compliance requirements and formal letters

    np_acts-logits-general · gemini-2.5-flash-lite

    The main thing this neuron does is pick out salient content nouns—especially proper nouns and key topic words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    ار
    0.96
    ak
    0.94
    ar
    0.80
    اگ
    0.79
    سب
    0.75
    r
    0.73
    ش
    0.72
    ارم
    0.71
    i
    0.71
    ir
    0.70
    POSITIVE LOGITS
     polytopes
    0.87
     locatie
    0.84
    జేపీ
    0.83
    
    0.82
     Unterschiede
    0.82
    ♎
    0.81
     σήμερα
    0.81
     padrões
    0.80
     énfasis
    0.80
     vandaag
    0.80
    Activations Density 0.018%

    No Known Activations