© 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. 7220
    Prev
    Next
    INDEX
    Explanations

    plans equivalents

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

    The neuron fires strongly on relatively rare or distinctive content words (longer, semantically loaded nouns, verbs, or adjectives).

    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
     Tutt
    0.78
     Maths
    0.76
     stesso
    0.76
     Possible
    0.76
     Sketches
    0.76
     sbParams
    0.74
     albums
    0.73
    𝐬
    0.73
     historique
    0.73
     Tutorials
    0.73
    POSITIVE LOGITS
     తొ
    0.80
    id
    0.80
     вызыва
    0.74
    anía
    0.72
    вшая
    0.71
     tecnológicas
    0.70
    엎
    0.70
     청
    0.70
    ach
    0.69
    держа
    0.68
    Activations Density 0.000%

    No Known Activations