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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7458
    Prev
    Next
    INDEX
    Explanations

    color: value

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

    The neuron strongly activates on mentions of “color” (and its spelling variants like “colour,” “palette,” “recolour,” etc.).

    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_31_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
     pyrite
    0.59
     veneer
    0.55
    humid
    0.55
    trombone
    0.54
     spacers
    0.54
    掰
    0.54
     tearing
    0.53
    貼り
    0.53
    Fluor
    0.53
    trajectory
    0.52
    POSITIVE LOGITS
     Αν
    0.66
     Mudah
    0.66
    ruptcy
    0.65
     Αυ
    0.64
     高校
    0.63
     chave
    0.63
     管理
    0.62
     Ры
    0.62
     必要
    0.61
     黑
    0.59
    Activations Density 0.003%

    No Known Activations