© 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. 7183
    Prev
    Next
    INDEX
    Explanations

    def read

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

    The neuron fires strongly on words that begin a sentence or new block of text, essentially marking sentence-initial tokens.

    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
    ắn
    0.90
     parecen
    0.85
     ozbil
    0.84
     qubits
    0.81
     adicionales
    0.81
    HeightSizeMode
    0.81
     $=$
    0.80
     серьез
    0.80
     CHCl
    0.80
     gegevens
    0.79
    POSITIVE LOGITS
    굽
    0.75
    ном
    0.73
    مار
    0.72
    اعد
    0.70
     Utd
    0.68
    EN
    0.66
    NOM
    0.66
    িক
    0.64
    го
    0.64
    ल
    0.64
    Activations Density 0.000%

    No Known Activations