© 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. 12240
    Prev
    Next
    INDEX
    Explanations

    The neuron is primarily firing on the special “<bos>” token, i.e. the beginning-of-sequence/ sentence marker.

    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
     on
    0.78
     in
    0.76
     at
    0.72
     ashore
    0.70
     within
    0.68
     steeped
    0.66
    .¹
    0.66
     from
    0.64
     along
    0.64
     bestowed
    0.64
    POSITIVE LOGITS
    C
    0.57
    N
    0.55
    J
    0.54
    K
    0.53
    G
    0.51
    V
    0.51
    T
    0.51
     ArrayRef
    0.50
    E
    0.50
    P
    0.50
    Activations Density 0.193%

    No Known Activations