© 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. 10-GEMMASCOPE-RES-131K
    4. 123758
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and variables

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

    mathematical notation with subscripts in academic or scientific text.

    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_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
     enables
    -2.31
     oscuro
    -2.25
     allows
    -2.25
    1
    -2.23
     makes
    -2.13
     uses
    -2.11
     should
    -2.09
     does
    -2.08
     enhances
    -2.06
    2
    -2.05
    POSITIVE LOGITS
    蛩
    2.30
    蛲
    2.23
    苁
    2.11
    艄
    2.08
    “.
    2.02
    鲩
    2.00
    锨
    2.00
     nebst
    2.00
    และ
    1.99
     considérée
    1.98
    Activations Density 0.018%

    No Known Activations