© 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. 10-GEMMASCOPE-RES-131K
    7. 111150
    Prev
    Next
    INDEX
    Explanations

    there and there too

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

    The neuron activates on locative expressions—that is, words referring to places or directions.

    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
     plausible
    -2.20
    л
    -1.97
    -1.91
     erste
    -1.84
     ""))
    -1.83
    两位
    -1.82
    ly
    -1.78
     if
    -1.76
    ):
    -1.73
     ""));
    -1.73
    POSITIVE LOGITS
    臵
    2.19
    
    2.16
    鹋
    2.05
    mäßigen
    2.02
    未来
    1.93
    ׄ
    1.93
     describe
    1.89
    瑒
    1.88
     upra
    1.87
    阋
    1.85
    Activations Density 0.001%

    No Known Activations