© 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. 49273
    Prev
    Next
    INDEX
    Explanations

    acceptable, allowed, okay, permissible, right

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

    The neuron is keyed to copular verbs—especially forms of “to be” (is, are, ’s, be, 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
    ylus
    -0.85
    ceğiniz
    -0.81
    engono
    -0.80
     évident
    -0.78
    明显的
    -0.78
    istaa
    -0.77
    nitten
    -0.77
     obvio
    -0.77
    CompoundButton
    -0.76
     joan
    -0.76
    POSITIVE LOGITS
     okay
    4.88
     OK
    4.56
     acceptable
    4.34
     ok
    4.34
    OK
    3.69
    Okay
    3.34
     Okay
    3.27
    okay
    3.27
    acceptable
    3.13
     Ok
    3.03
    Activations Density 0.070%

    No Known Activations