© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 78473
    Prev
    Next
    INDEX
    Explanations

    starts sentence with "I"

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

    The neuron triggers on tokens used as informal discourse markers or asides—e.g. emoticons, parentheses, ellipses, and similar transition/punctuation cues.

    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
    
    -0.99
    Hope
    -0.97
    注意
    -0.97
     vru
    -0.96
     REMEMBER
    -0.96
    たまに
    -0.95
     moſt
    -0.93
    odine
    -0.93
     anyone
    -0.91
     namens
    -0.91
    POSITIVE LOGITS
     will
    1.68
     do
    1.66
     I
    1.39
     Perhaps
    1.37
     might
    1.34
     Thanks
    1.34
     thanks
    1.23
     misschien
    1.23
     If
    1.22
     Since
    1.22
    Activations Density 0.011%

    No Known Activations