© 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. 13026
    Prev
    Next
    INDEX
    Explanations

    chemical suffixes CH COOH

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

    mathematical notation, particularly symbols, operators, and variables in equations and formulas.

    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
     may
    -1.16
     even
    -1.10
     might
    -1.10
     will
    -1.09
     probably
    -1.05
     this
    -1.05
     Because
    -1.05
     During
    -1.02
     new
    -1.01
     are
    -1.00
    POSITIVE LOGITS
     tamaños
    1.13
     brazilian
    1.13
    摀
    1.09
     envíos
    1.05
     vendredi
    1.05
     soumettre
    1.02
     producteurs
    1.01
     Atención
    1.01
     tivi
    1.00
     compatri
    0.99
    Activations Density 0.128%

    No Known Activations