© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9127
    Prev
    Next
    INDEX
    Explanations

    Epicurus, Euler, Mach, Compatibility

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

    The neuron fires on marketing-style verbs that promise or provide features or services (e.g., “promises,” “provides,” “offering”).

    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
    0.77
     labor
    0.74
     laborer
    0.73
     Financial
    0.73
     labors
    0.70
     unending
    0.68
     navigable
    0.67
    ין
    0.67
    ilea
    0.67
     sometime
    0.66
    POSITIVE LOGITS
    ◙
    0.87
    🗸
    0.82
    ❊
    0.82
     अनुर
    0.80
     desenhos
    0.80
     Preta
    0.77
    distances
    0.75
    Pharmac
    0.75
    phosphorylation
    0.75
     ciências
    0.73
    Activations Density 0.001%

    No Known Activations