© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26545
    Prev
    Next
    INDEX
    Explanations

    Alamofire, Loader, sqlite

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

    The neuron fires strongly on names of external libraries or frameworks (e.g. Alamofire, Universal Image Loader, Tornado) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     fatte
    -1.41
     emballage
    -1.36
    tım
    -1.35
     balkon
    -1.33
     Kristus
    -1.30
     berta
    -1.30
    뺀
    -1.30
     would
    -1.30
    勠
    -1.30
    klere
    -1.28
    POSITIVE LOGITS
    などが
    1.51
    <bos>
    1.46
     PUSTAKA
    1.40
    她是
    1.28
    1
    1.21
    釓
    1.20
    了她
    1.19
    了些
    1.16
    などなど
    1.15
     Präsidenten
    1.15
    Activations Density 0.001%

    No Known Activations