© 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. 27502
    Prev
    Next
    INDEX
    Explanations

    in followed by place names

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

    The neuron strongly activates on the preposition “in,” particularly when it introduces a place name or location context.

    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
     “
    -1.11
    ’
    -1.10
    ‑
    -1.08
     the
    -1.05
     acheteurs
    -1.04
    '
    -1.04
    ds
    -1.02
    against
    -1.02
    unno
    -1.00
     מספר
    -1.00
    POSITIVE LOGITS
     navegando
    1.11
    なんですよ
    1.07
     from
    1.04
    Plays
    1.03
    bearded
    1.02
     υπάρχ
    1.02
     wła
    1.00
    罔
    0.98
    turnstile
    0.98
    spanish
    0.98
    Activations Density 0.043%

    No Known Activations