© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83119
    Prev
    Next
    INDEX
    Explanations

    person who reads

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

    The neuron strongly activates on occurrences of the word “Reader” (or “reader”)—it flags that specific token.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    <em>
    -1.36
    x
    -1.26
    e
    -1.14
    u
    -1.08
    y
    -1.05
    扎
    -1.05
    /*
    -1.02
    <sup>
    -1.01
    v
    -0.99
    蓠
    -0.99
    POSITIVE LOGITS
     Reader
    1.47
     READER
    1.45
     readers
    1.41
    グルト
    1.35
     Readers
    1.30
    猡
    1.25
     reader
    1.23
    ❕
    1.21
     gemeenten
    1.21
    readers
    1.20
    Activations Density 0.011%

    No Known Activations