© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 14050
    Prev
    Next
    INDEX
    Explanations

    one / someone

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

    This neuron activates on evaluative or opinionated statements—phrases that express praise, judgments, or recommendations.

    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
    এবং
    0.94
     selves
    0.84
     మరియు
    0.76
    ங்களையும்
    0.75
     உள்ளன
    0.75
     democracies
    0.75
    蟶
    0.73
     padrões
    0.73
     niveles
    0.71
    に加え
    0.71
    POSITIVE LOGITS
     atau
    1.40
     или
    1.37
     หรือ
    1.34
     یا
    1.30
     কিংবা
    1.28
     或者
    1.27
    或者是
    1.26
     或
    1.24
     किंवा
    1.22
     või
    1.21
    Activations Density 1.044%

    No Known Activations