© 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. 1222
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and associated attributes

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

    The neuron fires on positive evaluative language—words expressing praise or gratitude (e.g. “your,” “exceptional,” “timely,” 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
     aktivi
    -1.12
     ekst
    -1.02
     ekster
    -1.02
     abuser
    -1.00
     praktis
    -0.99
     papir
    -0.93
     kompeti
    -0.91
     lej
    -0.91
     rezerv
    -0.89
     kriminal
    -0.88
    POSITIVE LOGITS
     website
    1.70
     system
    1.37
     services
    1.34
     methods
    1.23
     advice
    1.21
     expertise
    1.20
     policies
    1.17
     recommendation
    1.16
     version
    1.16
     influence
    1.16
    Activations Density 0.044%

    No Known Activations