© 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. 111122
    Prev
    Next
    INDEX
    Explanations

    http:// pattern

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

    URL protocols (http://) and abbreviated technical terms in code and scientific documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     last
    -1.60
    </h3>
    -1.34
    それほど
    -1.32
     yesterday
    -1.28
    のも
    -1.22
    at
    -1.21
     fides
    -1.21
     neues
    -1.18
    j
    -1.15
    ne
    -1.13
    POSITIVE LOGITS
    sepatu
    1.40
     másik
    1.39
    mizuno
    1.35
     兒童
    1.34
    rischen
    1.34
     enemigo
    1.33
     fekete
    1.32
     csalá
    1.31
    出典
    1.31
     különböző
    1.30
    Activations Density 0.257%

    No Known Activations