© 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. 10-GEMMASCOPE-RES-131K
    7. 60516
    Prev
    Next
    INDEX
    Explanations

    live in

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

    The neuron flags first‐person statements of residence—especially occurrences of “live in” (i.e. “I live in [place]”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    cún
    -1.41
    fokus
    -1.41
     verschiedener
    -1.37
     grandiose
    -1.36
     různých
    -1.36
    닙
    -1.33
    nossa
    -1.33
    και
    -1.31
     różnych
    -1.30
    recette
    -1.30
    POSITIVE LOGITS
     also
    1.72
     =
    1.45
     currently
    1.35
     також
    1.32
     aussi
    1.31
     appris
    1.31
    尚未
    1.30
    Champaign
    1.30
     également
    1.29
    t
    1.27
    Activations Density 0.043%

    No Known Activations