© 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. 2326
    Prev
    Next
    INDEX
    Explanations

    logos or displays

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

    This neuron fires on the demonstrative/existential “here” or “there” token when it introduces a clause.

    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
    ما
    0.81
    cuno
    0.79
    ولي
    0.75
    丸
    0.72
    АК
    0.71
    ADO
    0.70
    وا
    0.70
    苋
    0.69
    في
    0.68
    建造
    0.68
    POSITIVE LOGITS
     schließlich
    0.84
     reloj
    0.74
     Funktions
    0.70
    thirsty
    0.70
     zelf
    0.69
     sổ
    0.69
     குழந்தையின்
    0.68
     свое
    0.67
    йдз
    0.67
    imise
    0.67
    Activations Density 0.000%

    No Known Activations