© 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. 2575
    Prev
    Next
    INDEX
    Explanations

    formatting and separators

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

    This neuron fires strongly on the very first token of each new text segment or paragraph (i.e. it detects segment/paragraph beginnings).

    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
    ​,
    0.60
     või
    0.55
    ǎ
    0.54
     €,
    0.54
    संच
    0.54
     calam
    0.52
     intras
    0.50
     ʻ
    0.49
    
    0.49
    équip
    0.48
    POSITIVE LOGITS
    ================
    3.00
    ----------------
    2.94
    ****************
    2.91
    ################
    2.75
    ////////////////
    2.58
    --------------
    2.56
    -------------
    2.52
    ============
    2.48
    ++++++++++++++++
    2.48
    ==============
    2.48
    Activations Density 0.051%

    No Known Activations