© 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. 117372
    Prev
    Next
    INDEX
    Explanations

    without + action or state

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

    The neuron is highly sensitive to the word “without,” especially when it introduces a clause (e.g. “without adding,” “without charging,” etc.).

    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
    などは
    -1.11
     solch
    -1.11
     solchen
    -1.09
    などが
    -1.09
     not
    -1.07
     when
    -1.07
     potrebbe
    -1.02
     sorento
    -1.00
    某个
    -1.00
     could
    -0.99
    POSITIVE LOGITS
    ต้อง
    1.47
     ohne
    1.30
     necesidad
    1.28
    sacrifice
    1.28
     harus
    1.27
     sacrificing
    1.27
     sacrifice
    1.26
     need
    1.23
     نیاز
    1.23
    necessarily
    1.21
    Activations Density 0.035%

    No Known Activations