© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67333
    Prev
    Next
    INDEX
    Explanations

    ended up [verb]

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

    The neuron activates on mentions of numeric measures or quantifiable statistics (numbers, ordinals, counts, etc.).

    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
     now
    -1.80
     not
    -1.23
     NOW
    -1.20
     currently
    -1.15
    гом
    -1.14
    böz
    -1.13
     one
    -1.11
     tĩnh
    -1.11
     been
    -1.10
    Pozri
    -1.10
    POSITIVE LOGITS
     nawet
    1.41
     حتی
    1.23
     vários
    1.23
     inteiro
    1.19
     tempore
    1.13
     sogar
    1.13
     alcune
    1.13
    🧪
    1.13
    acuzzi
    1.13
    了不少
    1.12
    Activations Density 0.037%

    No Known Activations