© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34908
    Prev
    Next
    INDEX
    Explanations

    random selection

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

    The neuron flags first‐person “I” statements and request‐phrases (e.g. “I want/need to…,” “How to…”) in programming‐question contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Fluss
    -0.98
     expect
    -0.94
     ہ
    -0.93
     to
    -0.92
     for
    -0.92
     everything
    -0.88
    如有
    -0.88
    靱
    -0.88
     دارند
    -0.87
     maybe
    -0.86
    POSITIVE LOGITS
     lựa
    1.02
    Selecting
    1.01
    Selection
    0.98
    挑选
    0.91
     it
    0.90
     escolher
    0.87
     Selecting
    0.86
    Choosing
    0.86
    amaño
    0.85
     sélectionner
    0.85
    Activations Density 0.005%

    No Known Activations