© 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. 104722
    Prev
    Next
    INDEX
    Explanations

    names and phrases after keywords

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

    This neuron spotlights version‐number strings—numbers appearing after a dot in typical software version headers.

    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
    歺
    -1.10
     Batalla
    -1.04
     szczególnie
    -1.04
     pasirink
    -1.03
     vinyle
    -1.01
    ({
    -0.97
     vidéos
    -0.94
     faſt
    -0.93
    лерея
    -0.90
     ganchillo
    -0.90
    POSITIVE LOGITS
    Y
    1.19
    J
    1.04
    el
    1.01
    EL
    0.97
    n
    0.97
    E
    0.97
     início
    0.94
    是怎么回事
    0.93
    ar
    0.93
    W
    0.93
    Activations Density 0.000%

    No Known Activations