© 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. 22-GEMMASCOPE-RES-131K
    4. 69227
    Prev
    Next
    INDEX
    Explanations

    money, work, usage, limit, program, wanna, discretion, executable

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

    The neuron picks out the single most “salient” content word in each text snippet—i.e. the key topic word or head noun/verb that best summarizes that segment.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     with
    -1.27
    時間で
    -1.05
    bernador
    -0.94
     GIS
    -0.91
    di
    -0.91
     without
    -0.90
    って思
    -0.88
    ۦ
    -0.86
    時間も
    -0.86
    m
    -0.85
    POSITIVE LOGITS
     zaterdag
    1.29
    !",
    1.28
    !");
    1.20
    ՛
    1.16
    !',
    1.13
    !";
    1.12
    !
    
    1.09
    !");
    
    1.09
    !\
    1.08
    !!"
    1.06
    Activations Density 0.038%

    No Known Activations