© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 833
    Prev
    Next
    INDEX
    Explanations

    code identifiers and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    omnie
    -0.82
     Swaziland
    -0.78
     nascita
    -0.77
    ኣ
    -0.73
     manifestazione
    -0.73
     cemeteries
    -0.72
     Nug
    -0.70
     parrot
    -0.70
     Prudence
    -0.70
     Eighteenth
    -0.70
    POSITIVE LOGITS
    trate
    0.70
     મ
    0.69
     Numerade
    0.66
    filtr
    0.66
    planet
    0.65
     renseignements
    0.63
     bonded
    0.62
    訪
    0.61
     praia
    0.61
     Gaw
    0.61
    Activations Density 0.065%

    No Known Activations