© 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. 11678
    Prev
    Next
    INDEX
    Explanations

    clothing items and locations

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

    The neuron fires on words that name people or describe social interactions and emotions in a story (e.g. friends, bully, sad, crying, help).

    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
     -
    0.99
    —
    0.88
     –
    0.85
     &
    0.84
    –
    0.80
     ostensibly
    0.80
     esche
    0.74
     nominally
    0.73
     —
    0.73
    --
    0.72
    POSITIVE LOGITS
     hauptsächlich
    1.13
     alot
    1.13
    됬
    1.10
     அதாவது
    1.09
     bisschen
    1.07
     deoarece
    1.07
     meisten
    1.06
    すごく
    1.05
     ähm
    1.05
     idk
    1.03
    Activations Density 0.007%

    No Known Activations