© 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. 109590
    Prev
    Next
    INDEX
    Explanations

    structural attributes

    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
    corrhi
    -0.84
    iibo
    -0.80
    zji
    -0.80
    !】
    -0.78
    gelen
    -0.78
    pande
    -0.77
     klasy
    -0.76
    tract
    -0.75
    🧵
    -0.74
    álogo
    -0.73
    POSITIVE LOGITS
     đấy
    0.82
    に到着
    0.75
     unterschiedlich
    0.71
     killings
    0.70
    ungszeit
    0.69
     forêt
    0.69
     Mel
    0.68
     currentPage
    0.68
     ähnliche
    0.68
    -*
    0.67
    Activations Density 0.000%

    No Known Activations