© 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. 578
    Prev
    Next
    INDEX
    Explanations

    i can

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

    This neuron activates on first-person statements, especially occurrences of “I” and related self-referential verbs expressing personal opinions or experiences.

    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
     münchen
    -1.05
     Gouver
    -1.03
     hablaba
    -1.02
    ppings
    -0.99
     it
    -0.98
     kompeti
    -0.98
    ница
    -0.98
     signifikan
    -0.97
     verdient
    -0.97
     púb
    -0.96
    POSITIVE LOGITS
     weiteres
    1.11
     drugi
    1.09
     großes
    1.04
     kleines
    1.03
    "");
    1.01
     כשה
    0.99
    "")
    0.99
     earlier
    0.99
     ganzes
    0.98
     najwyżs
    0.98
    Activations Density 0.052%

    No Known Activations