© 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. 22-GEMMASCOPE-RES-131K
    7. 67807
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns

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

    The neuron fires on bare‐form (infinitive) verbs (e.g. free, protect, disguise, hide, draw, afflict, reinvent, console).

    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
     here
    -1.68
     to
    -1.39
     such
    -1.35
     also
    -1.25
     таких
    -1.20
     Such
    -1.13
     такие
    -1.13
     It
    -1.11
     такого
    -1.10
    Према
    -1.09
    POSITIVE LOGITS
     himself
    2.77
     yourself
    2.73
     themselves
    2.69
     oneself
    2.56
    ตัวเอง
    2.53
     herself
    2.39
     ourselves
    2.34
     себя
    2.28
     myself
    2.25
     خود
    2.02
    Activations Density 0.036%

    No Known Activations