© 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. 2639
    Prev
    Next
    INDEX
    Explanations

    transition words

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

    The neuron detects paragraph breaks or blank‐line/newline 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
     使っ
    1.14
     聞い
    1.11
     blossomed
    1.07
     tangy
    1.06
     多く
    1.05
     関係
    1.05
     ស
    1.02
     本当
    1.01
     คะแนน
    1.01
     寝
    0.98
    POSITIVE LOGITS
    (
    1.20
    ________________
    1.05
    http
    1.04
    No
    1.04
    "
    1.04
    </
    1.03
    The
    1.02
    ка
    1.02
    English
    1.02
    >
    1.02
    Activations Density 0.015%

    No Known Activations