© 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. 5490
    Prev
    Next
    INDEX
    Explanations

    """Docstring"""

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

    The neuron strongly activates on infrequent or unusual tokens—especially proper names or rare content words.

    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
    োনায়
    0.72
    կ
    0.71
     quieran
    0.69
     realizan
    0.66
    鸪
    0.66
    ORO
    0.65
    ੍ਹਾਂ
    0.64
     DataTypes
    0.64
    ਡ
    0.64
    一个个
    0.63
    POSITIVE LOGITS
    vä
    0.75
     embroidered
    0.73
    höhe
    0.72
     expediente
    0.71
    remarkable
    0.71
    ью
    0.70
     huyền
    0.70
    vorm
    0.70
     Sergei
    0.69
    ரும்
    0.69
    Activations Density 0.000%

    No Known Activations