© 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. 34-GEMMASCOPE-RES-131K
    4. 11846
    Prev
    Next
    INDEX
    Explanations

    file and its descriptive text

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

    the presence of the word “file,” especially in code comments or filenames.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Ghost
    -0.77
     sebagainya
    -0.75
     on
    -0.75
     förr
    -0.73
    fra
    -0.73
    Fra
    -0.71
     Indians
    -0.70
     đen
    -0.70
    hoty
    -0.69
     Arboretum
    -0.68
    POSITIVE LOGITS
    tiu
    0.83
    overview
    0.80
    atime
    0.80
    层
    0.80
    pisode
    0.80
    ARDI
    0.76
    ⡾
    0.76
    eddah
    0.76
     Niem
    0.75
     层
    0.74
    Activations Density 0.048%

    No Known Activations