© 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. 22-GEMMASCOPE-RES-131K
    7. 38931
    Prev
    Next
    INDEX
    Explanations

    skill and concentration

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

    This neuron flags language expressing requirements, necessities, or obligations (e.g. “had to be…in order to,” “requires,” “takes a toll,” “Only…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
     once
    -1.33
     after
    -1.16
     thanks
    -1.11
     when
    -1.09
    tacular
    -1.08
     why
    -1.08
     tell
    -1.07
    ebenarnya
    -1.06
     soon
    -1.06
    ergic
    -1.03
    POSITIVE LOGITS
     nécessairement
    1.09
     délicieux
    1.09
     skills
    1.05
     extrême
    1.05
    endaten
    1.04
     skill
    1.03
    мання
    1.02
     csomag
    1.02
     stamina
    1.01
     habile
    1.00
    Activations Density 0.024%

    No Known Activations