© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71881
    Prev
    Next
    INDEX
    Explanations

    xml namespaces

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

    The neuron fires on URL/URI components (especially the “http://” scheme and related domain/schema fragments) in markup.

    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
    ྃ
    -1.49
    kset
    -1.38
    incón
    -1.31
    盉
    -1.23
    炱
    -1.22
     exitosa
    -1.21
    itectura
    -1.21
     perché
    -1.20
    ༛
    -1.20
    zzles
    -1.20
    POSITIVE LOGITS
     of
    1.99
     with
    1.43
    </
    1.35
    .
    1.34
     simple
    1.28
     "}";
    1.27
    Etimología
    1.26
     a
    1.23
     paroisse
    1.16
     لم
    1.13
    Activations Density 0.107%

    No Known Activations