© 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. 22-GEMMASCOPE-RES-131K
    7. 26699
    Prev
    Next
    INDEX
    Explanations

    describing potential outcomes

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

    The neuron is detecting occurrences of the word “can,” i.e. the modal auxiliary “can.”

    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
    accéder
    -1.30
    ogical
    -1.30
    nological
    -1.17
     què
    -1.16
     сможет
    -1.11
    ciled
    -1.09
     homoto
    -1.07
     pérd
    -1.06
    ⿰
    -1.05
     stap
    -1.04
    POSITIVE LOGITS
     sometimes
    1.51
     also
    1.34
     også
    1.27
    ashes
    1.26
     incluso
    1.24
     be
    1.23
     både
    1.20
     very
    1.17
     бывает
    1.16
     even
    1.16
    Activations Density 0.060%

    No Known Activations