© 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. 24-GEMMASCOPE-2-RES-16K
    7. 2955
    Prev
    Next
    INDEX
    Explanations

    code examples or descriptions

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

    The neuron fires on named technical tools, platforms, or branded UI components (e.g. “Immediate window,” “Aula web,” “Transport Request,” “Hammer Editor”).

    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
    𓃵
    0.59
    ционе
    0.58
    addena
    0.55
     Prosperity
    0.53
     Pran
    0.53
    лекет
    0.52
     Partai
    0.52
    таны
    0.52
    뻑
    0.50
    父親
    0.50
    POSITIVE LOGITS
    f
    0.70
    al
    0.66
    ed
    0.64
    on
    0.62
     diagrams
    0.59
    b
    0.59
    _
    0.59
    an
    0.58
     analyzer
    0.58
    F
    0.58
    Activations Density 0.000%

    No Known Activations