© 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. 10-GEMMASCOPE-RES-131K
    7. 73443
    Prev
    Next
    INDEX
    Explanations

    be + past participle or adjective

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

    The neuron fires on auxiliary “modal” verbs (e.g. can, could, should, shall) and passive‐voice “be” constructions indicating possibility or 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_10/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
    },
    -2.98
    s
    -2.88
     wasser
    -2.84
    
    -2.83
    pheric
    -2.81
    噐
    -2.78
    偁
    -2.77
    mination
    -2.75
    沨
    -2.73
    their
    -2.69
    POSITIVE LOGITS
     able
    3.27
     termed
    2.92
     regarded
    2.88
     considered
    2.47
     be
    2.38
     “
    2.33
     used
    2.30
    *
    2.19
     F
    2.17
     construed
    2.17
    Activations Density 0.248%

    No Known Activations