© 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. 10-GEMMASCOPE-RES-131K
    7. 60688
    Prev
    Next
    INDEX
    Explanations

    items listed or described

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

    The neuron is detecting occurrences of the word “list” in its inflected forms (e.g. “listed,” “listings”).

    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
    {
    -3.50
    }
    -2.47
        
    -2.28
     основании
    -2.20
    2
    -2.14
     практике
    -2.14
     човек
    -2.14
     για
    -2.11
    z
    -2.06
     một
    -2.03
    POSITIVE LOGITS
    身边的
    2.55
    猡
    2.52
    listed
    2.45
    赁
    2.44
    </h3>
    2.42
     ‚
    2.39
    勦
    2.38
    ’，
    2.36
    ות
    2.34
    裊
    2.33
    Activations Density 0.010%

    No Known Activations