© 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. 34-GEMMASCOPE-RES-131K
    7. 65050
    Prev
    Next
    INDEX
    Explanations

    can be used

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

    This neuron fires on modal auxiliary verbs (e.g. can, may, should) indicating possibility or permission.

    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
    vejte
    -0.86
    matous
    -0.84
    Hire
    -0.81
    hashtag
    -0.79
    Adopt
    -0.79
    が存在
    -0.78
    Worship
    -0.77
    🧒
    -0.77
     Adopt
    -0.77
    こんばんは
    -0.76
    POSITIVE LOGITS
     used
    3.55
     digunakan
    2.70
     Used
    2.47
    Used
    2.44
     используется
    2.27
    used
    2.23
    用于
    2.22
     χρησιμοποι
    2.09
     brukes
    2.05
    用来
    2.03
    Activations Density 0.207%

    No Known Activations