© 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. 14223
    Prev
    Next
    INDEX
    Explanations

    name and title

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

    The neuron fires on the “.” (dot) token when used as a member‐access operator in code.

    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
     berge
    -1.39
     brancas
    -1.31
     vermelhas
    -1.28
    reiten
    -1.25
     correcte
    -1.23
     configurações
    -1.23
     stoff
    -1.20
     tempel
    -1.20
     minimalis
    -1.19
     favoris
    -1.17
    POSITIVE LOGITS
     valiant
    1.10
    了自己
    1.05
    k
    1.05
     houve
    1.02
     jemanden
    1.02
    全程
    1.02
     dokonce
    1.00
    ut
    0.99
    ύτε
    0.98
     offenbar
    0.98
    Activations Density 0.000%

    No Known Activations