© 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. 48046
    Prev
    Next
    INDEX
    Explanations

    PHP file extensions and licenses

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

    The neuron responds to uppercase technical identifiers and constants (e.g. config keys, license tags, macro-like tokens) 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_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
     Vitamina
    -1.23
     excluding
    -1.18
     includ
    -1.15
     Desta
    -1.09
     图片
    -1.08
    = 
    -1.06
     ingenu
    -1.05
    calm
    -1.05
     diversa
    -1.05
    noob
    -1.05
    POSITIVE LOGITS
     одному
    1.16
    сах
    1.12
    nero
    1.09
    。】
    1.06
     destiné
    1.05
     your
    1.05
    )[
    1.05
    ｰ
    1.04
    メーター
    1.04
    omio
    1.03
    Activations Density 0.144%

    No Known Activations