© 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. 22-GEMMASCOPE-RES-131K
    7. 34877
    Prev
    Next
    INDEX
    Explanations

    websites and URLs

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

    The neuron detects website domain names in URLs (e.g. “youtube,” “facebook,” “wikipedia,” “imdb,” 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_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
     that
    -1.77
     in
    -1.40
     jūsų
    -1.26
     a
    -1.24
     That
    -1.20
    lético
    -1.19
    Any
    -1.18
     on
    -1.17
    ledad
    -1.17
    getMenuInflater
    -1.15
    POSITIVE LOGITS
    OBJETIVO
    1.53
    appartement
    1.33
     maniere
    1.28
    wherein
    1.27
     reager
    1.26
     geze
    1.23
    熾
    1.22
    quirer
    1.20
    Nieuwe
    1.19
    OBJETIVOS
    1.18
    Activations Density 0.024%

    No Known Activations