© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15424
    Prev
    Next
    INDEX
    Explanations

    desire greater, promising new

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

    The neuron fires on content-bearing, topic-specific words (the key nouns, verbs, and adjectives) rather than on common function 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
    0.78
     دیگر
    0.70
     data
    0.69
     dati
    0.68
     versucht
    0.68
    }
    0.68
    data
    0.68
     datos
    0.67
    ALOG
    0.67
    തന്നെ
    0.67
    POSITIVE LOGITS
    aient
    0.93
    ić
    0.87
    ično
    0.84
    椃
    0.84
    ാൻഡ്
    0.82
    ੀ
    0.80
    वय
    0.79
    redients
    0.78
    მას
    0.76
    ઉસ
    0.75
    Activations Density 0.000%

    No Known Activations