© 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. 111076
    Prev
    Next
    INDEX
    Explanations

    unspecified or broad references

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

    The neuron fires on occurrences of the word “anything.”

    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
     and
    -1.76
     gimnasio
    -1.39
    一个
    -1.23
     ”
    -1.20
     reveal
    -1.16
    urcht
    -1.16
    WANT
    -1.13
     iliş
    -1.13
     –
    -1.13
     …”
    -1.13
    POSITIVE LOGITS
     weet
    1.45
    quirer
    1.45
     latar
    1.42
     damen
    1.42
    ating
    1.40
     guld
    1.38
     medan
    1.38
     jei
    1.38
    acheco
    1.37
     umbro
    1.36
    Activations Density 0.003%

    No Known Activations