© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66734
    Prev
    Next
    INDEX
    Explanations

    chemical formulas containing numbers

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

    numbers in technical or scientific contexts, particularly in chemical formulas and mathematical expressions.

    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
     ESCAPE
    -1.08
    itated
    -0.90
     вік
    -0.88
     ハウス
    -0.84
    ziell
    -0.82
     Surveillance
    -0.82
    ريقيا
    -0.82
    解釋
    -0.81
    IndexPath
    -0.81
     peč
    -0.81
    POSITIVE LOGITS
    にかけて
    1.01
    と思う
    0.90
    十分
    0.87
     soltanto
    0.85
     vanguardia
    0.85
     Hingga
    0.84
    Getenv
    0.83
    iev
    0.82
     nuestro
    0.82
     والأ
    0.81
    Activations Density 0.207%

    No Known Activations