© 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. 39921
    Prev
    Next
    INDEX
    Explanations

    signal transduction

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

    references to signals and signal transduction in scientific and technical contexts.

    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
     overriding
    -2.41
     هفت
    -2.22
    姈
    -2.19
    图为
    -2.14
    
    -2.09
    嫪
    -2.08
    떳
    -2.08
    ޕ
    -2.06
    ኑ
    -2.03
    ätigung
    -2.02
    POSITIVE LOGITS
    u
    2.56
    man
    2.47
    も良い
    2.45
    son
    2.42
     determinar
    2.23
     Perché
    2.23
    
    2.19
    mètre
    2.13
    ATIVES
    2.11
    攥
    2.11
    Activations Density 0.026%

    No Known Activations