© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78596
    Prev
    Next
    INDEX
    Explanations

    words ending in atter, etter, itter, utter

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

    The neuron fires on tokens containing a double "t" (i.e. “tt”) sequence.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     puberty
    -0.72
     切り
    -0.70
    Another
    -0.68
     誰
    -0.68
    carl
    -0.68
    改めて
    -0.68
    dika
    -0.68
    Cate
    -0.67
    regu
    -0.66
     näch
    -0.66
    POSITIVE LOGITS
    Box
    0.98
    idge
    0.94
    ATTER
    0.89
     box
    0.86
    rinology
    0.84
    BOX
    0.83
    电池
    0.82
    ruptcy
    0.81
    ?}",
    0.80
    ℘
    0.80
    Activations Density 0.018%

    No Known Activations