© 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. 41982
    Prev
    Next
    INDEX
    Explanations

    names, contracts, or tax details

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

    The neuron fires on technical or domain‐specific terminology.

    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
     on
    -1.98
     with
    -1.63
     as
    -1.45
     it
    -1.44
     will
    -1.43
     the
    -1.38
     others
    -1.30
     one
    -1.27
     It
    -1.26
     you
    -1.16
    POSITIVE LOGITS
     garantir
    1.41
     démoc
    1.33
     descobrir
    1.30
     relâche
    1.27
     naszego
    1.26
    usakan
    1.25
     confé
    1.24
     rafraî
    1.24
     célé
    1.23
     ориги
    1.23
    Activations Density 0.522%

    No Known Activations