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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8641
    Prev
    Next
    INDEX
    Explanations

    license types

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

    The neuron lights up on content‐bearing, “topic” words (i.e. nouns, verbs, and adjectives that carry substantive meaning) 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
    Setting
    0.71
    SAFE
    0.69
    MENT
    0.68
    familiar
    0.68
    ষ্ঠ
    0.67
    ου
    0.66
    у
    0.66
    Predicted
    0.66
    ⚠️
    0.66
    🖊
    0.65
    POSITIVE LOGITS
     cuya
    1.02
     hecha
    1.00
     hechas
    0.99
     llamadas
    0.96
     cuyas
    0.93
     adicion
    0.91
     trata
    0.89
     llam
    0.86
    م
    0.84
     asociada
    0.84
    Activations Density 0.000%

    No Known Activations