© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12765
    Prev
    Next
    INDEX
    Explanations

    hello and ready

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

    The neuron strongly activates on numeric measurements expressed as decimal values (floating‐point numbers) in the text.

    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
     Example
    0.75
     Пример
    0.63
    Example
    0.60
    }$$
    0.59
     Specification
    0.59
     Exemple
    0.59
     Сі
    0.58
     Ejemplo
    0.57
     Си
    0.57
     シ
    0.56
    POSITIVE LOGITS
     branche
    0.72
     inferiority
    0.63
     outpost
    0.61
     rendez
    0.61
     missile
    0.59
    ந்திய
    0.57
    旗下
    0.56
    -"
    0.55
    wati
    0.55
    ത്തിനും
    0.55
    Activations Density 0.000%

    No Known Activations