© 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. 8240
    Prev
    Next
    INDEX
    Explanations

    ------------- print board

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

    This neuron lights up on salient content words (verbs, adjectives, adverbs, pronouns) 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
    𝐬
    0.82
     setActive
    0.74
    Strategies
    0.73
    ⛄
    0.72
    嗅
    0.72
    ς
    0.71
    🛰
    0.70
    κά
    0.70
    ⌟
    0.69
    გენ
    0.68
    POSITIVE LOGITS
     mockery
    0.84
     Wally
    0.84
     fervent
    0.83
     Hitler
    0.80
     democr
    0.78
     ferv
    0.77
     idiots
    0.77
     Netanyahu
    0.76
     domingo
    0.76
     pitiful
    0.75
    Activations Density 0.001%

    No Known Activations