© 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. 22-GEMMASCOPE-RES-131K
    7. 40114
    Prev
    Next
    INDEX
    Explanations

    numbers and names

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

    The neuron activates on the repeated hex color code “#f2f2f2,” i.e. CSS background‐color specification.

    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
     from
    -1.53
     so
    -1.51
     in
    -1.46
     or
    -1.45
    еру
    -1.26
    ₽
    -1.21
     his
    -1.20
     an
    -1.20
     веке
    -1.17
     all
    -1.16
    POSITIVE LOGITS
     afore
    1.39
     ™
    1.27
    z
    1.21
     hervorge
    1.21
     těchto
    1.18
     weiterhin
    1.13
     idiotic
    1.13
    N
    1.12
     offenbar
    1.11
    O
    1.11
    Activations Density 0.000%

    No Known Activations