© 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. 9003
    Prev
    Next
    INDEX
    Explanations

    string, thread, cord, rope, yarn

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

    The main thing this neuron does is find references to long, flexible tying materials (e.g. strings, threads, cords).

    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
    𝘆
    -1.45
     there
    -1.37
     semblables
    -1.28
    
    -1.28
     itinéraires
    -1.27
     médec
    -1.27
    äsident
    -1.27
    ędziesz
    -1.25
    estão
    -1.24
    große
    -1.24
    POSITIVE LOGITS
    </h3>
    1.51
     OGSÅ
    1.43
    </i>
    1.42
     OWN
    1.28
    ть
    1.28
     cuándo
    1.23
     molest
    1.20
     OTHERWISE
    1.20
     PARTICULAR
    1.20
    чик
    1.20
    Activations Density 0.033%

    No Known Activations