© 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. 28137
    Prev
    Next
    INDEX
    Explanations

    non-negative cost, radius, violation parameter, chemical ions, integer arrays, dynamics, Q codes, Massachusetts insurers

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

    descriptions of technical properties in scientific or mathematical texts.

    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
     joyas
    -1.22
     their
    -1.09
     başlad
    -1.09
     bolsos
    -1.07
     peinados
    -1.06
     to
    -1.05
     Vierge
    -1.05
    揍
    -1.04
     utilizarse
    -1.04
    .«
    -1.04
    POSITIVE LOGITS
    Trayectoria
    1.13
    inine
    1.04
    asının
    1.03
    Élet
    1.00
    ダウンロード
    1.00
     рецепта
    0.98
    ῖν
    0.98
    しますね
    0.98
    はなく
    0.96
    Fabricante
    0.96
    Activations Density 0.003%

    No Known Activations