© 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. 22-GEMMASCOPE-RES-131K
    4. 79663
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by locations

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

    The neuron strongly responds to numeric tokens or figures (e.g., counts, measurements, years).

    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
     fumée
    -1.09
    <bos>
    -1.08
     chng
    -1.08
     bienfaits
    -1.07
     graisse
    -1.02
     frond
    -1.01
    齟
    -1.00
    ראות
    -0.99
    岿
    -0.96
     risques
    -0.96
    POSITIVE LOGITS
     our
    2.03
     jesteśmy
    1.11
     here
    1.09
    我们的
    1.07
    我们
    1.05
    ouage
    1.03
     all
    1.02
     of
    1.02
     within
    1.02
     nuestra
    1.00
    Activations Density 0.095%

    No Known Activations