© 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. 67240
    Prev
    Next
    INDEX
    Explanations

    code preamble and documentation markers

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

    the presence of underscore characters in tokens (e.g. identifiers or Emacs-style “-*-” markers)

    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
    共和国
    -0.96
     paillettes
    -0.96
    LTRB
    -0.96
    fgaben
    -0.93
    肥料
    -0.91
    NTSTATUS
    -0.91
    驟
    -0.91
    눅
    -0.90
     create
    -0.88
     знаете
    -0.88
    POSITIVE LOGITS
     sugerencias
    1.27
     тази
    1.18
    のご紹介
    1.15
     trám
    1.12
     actuales
    1.11
     requerimientos
    1.11
    excellents
    1.09
     richied
    1.08
     richiesto
    1.08
     народов
    1.07
    Activations Density 0.000%

    No Known Activations