© 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. 35228
    Prev
    Next
    INDEX
    Explanations

    latest news and updates

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

    The neuron strongly activates on the word “latest” when it appears in contexts announcing a new release or update.

    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
    (“
    -1.17
    órica
    -1.16
     presup
    -1.14
    nessy
    -1.13
    throughout
    -1.13
    Annexes
    -1.10
    ritage
    -1.10
    ulfon
    -1.10
     入っ
    -1.09
     créer
    -1.08
    POSITIVE LOGITS
     of
    1.82
     on
    1.52
     addition
    1.35
     updates
    1.29
     adds
    1.27
     additions
    1.20
     update
    1.20
     about
    1.14
     puts
    1.12
     includes
    1.07
    Activations Density 0.040%

    No Known Activations