© 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. 27044
    Prev
    Next
    INDEX
    Explanations

    the followed by question or number

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

    The neuron fires strongly on very common high-frequency English tokens (i.e. stopwords and other filler words).

    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
    ᐈ
    -1.52
    据说
    -1.51
    虽说
    -1.49
     élas
    -1.29
    ностью
    -1.23
     lukewarm
    -1.21
    зия
    -1.20
     [],
    -1.20
    ：……
    -1.20
    ：
    -1.19
    POSITIVE LOGITS
     other
    1.73
     others
    1.50
     same
    1.50
    !!!!!!
    1.47
     corresponding
    1.47
     locations
    1.45
     each
    1.38
     it
    1.38
     subsequent
    1.36
     calculation
    1.36
    Activations Density 0.121%

    No Known Activations