© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90804
    Prev
    Next
    INDEX
    Explanations

    now / formerly locations

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

    This neuron detects mentions of specific geographical place names.

    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
     eksklu
    -1.34
     defekt
    -1.33
     nuove
    -1.28
    both
    -1.26
     THEIR
    -1.24
     kram
    -1.23
     ekster
    -1.21
    Both
    -1.16
    Ссылки
    -1.15
    appointing
    -1.15
    POSITIVE LOGITS
     —
    1.28
     :
    1.27
    ):
    1.23
     ;
    1.12
     –
    1.09
    )
    1.05
     including
    1.01
     deriva
    1.01
    );
    1.00
     we
    1.00
    Activations Density 0.057%

    No Known Activations