© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82436
    Prev
    Next
    INDEX
    Explanations

    what can be done

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

    The neuron fires strongly on occurrences of the modal verbs “can” and “could” (expressions of ability).

    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
     âu
    -1.06
     ekolog
    -1.04
     enough
    -1.00
     damska
    -0.97
    Endian
    -0.96
    RTCF
    -0.95
     genug
    -0.94
    側は
    -0.93
    もうすぐ
    -0.91
    DebuggerNonUser
    -0.90
    POSITIVE LOGITS
     possibly
    2.05
     possible
    1.77
     to
    1.65
     muster
    1.41
     Possibly
    1.40
     get
    1.39
     while
    1.39
    possible
    1.35
    Possibly
    1.31
     think
    1.27
    Activations Density 0.021%

    No Known Activations