© 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. 22-GEMMASCOPE-RES-131K
    7. 68256
    Prev
    Next
    INDEX
    Explanations

    base and directory separators

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

    The neuron detects module or file names in import/require paths (the path segments following “./”, especially those with leading underscores or hyphens).

    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
     our
    -1.27
     their
    -1.27
     kwietnia
    -1.18
     lipca
    -1.16
     two
    -1.16
     września
    -1.14
     stycznia
    -1.13
     июня
    -1.06
     listopada
    -1.05
    EMOS
    -1.03
    POSITIVE LOGITS
    Ilustra
    1.42
    Mí
    1.37
    Gratis
    1.34
    Bety
    1.34
    توضیحات
    1.30
    Elke
    1.28
    Continua
    1.28
    Specifica
    1.26
    引用元
    1.25
    Oby
    1.23
    Activations Density 0.012%

    No Known Activations