© 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. 61189
    Prev
    Next
    INDEX
    Explanations

    finding information

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

    The neuron strongly activates on occurrences of the verb “find” (e.g. “find out,” “find your,” etc.).

    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
    寕
    -1.69
     varandra
    -1.52
    ․
    -1.50
    巨大的
    -1.48
     этим
    -1.42
    These
    -1.42
    
    -1.42
    妯
    -1.42
    ;
    -1.38
    comuna
    -1.38
    POSITIVE LOGITS
     a
    2.38
     which
    1.75
     where
    1.69
    皷
    1.65
     how
    1.48
    </u>
    1.46
     Its
    1.45
    最早
    1.42
     answer
    1.41
    </h4>
    1.40
    Activations Density 0.032%

    No Known Activations