© 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. 79856
    Prev
    Next
    INDEX
    Explanations

    sequence initiators

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

    letter or document formatting elements, particularly formal letter styles, titles, and structural elements.

    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
     cucchiaio
    -1.27
     trouva
    -1.13
     имеется
    -1.11
     имеются
    -1.08
     españ
    -1.08
     cucchia
    -1.07
     etc
    -1.07
     diku
    -1.07
     inasmuch
    -1.05
     блюда
    -1.05
    POSITIVE LOGITS
     rehabilitación
    1.10
     saudável
    1.10
     peuvent
    1.10
    ,
    1.10
     our
    1.06
     rapidamente
    1.05
     convocatoria
    1.03
     可愛い
    1.03
     probablement
    1.02
     τὴν
    1.02
    Activations Density 0.023%

    No Known Activations