© 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. 36412
    Prev
    Next
    INDEX
    Explanations

    scientific formulas and code snippets

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

    programming and mathematical syntax patterns like code blocks, formatting, and notation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    と感じ
    -0.97
     abnorm
    -0.94
    ButtonModule
    -0.91
     передний
    -0.88
    方的
    -0.87
    kiat
    -0.86
     enri
    -0.84
     …
    -0.84
     ihres
    -0.81
     comprehended
    -0.81
    POSITIVE LOGITS
    You
    1.15
     another
    1.05
    )
    1.01
     geloof
    0.96
     ()
    0.94
     aidé
    0.93
    ()")
    0.93
     expliqué
    0.93
    شهاد
    0.92
    >
    0.91
    Activations Density 0.128%

    No Known Activations