© 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. 49430
    Prev
    Next
    INDEX
    Explanations

    graph properties and labels

    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
     conni
    -0.81
    Ria
    -0.77
    dign
    -0.76
    SNA
    -0.75
    Acro
    -0.74
    NPS
    -0.71
     veilig
    -0.71
     taiwan
    -0.70
    bren
    -0.70
    miso
    -0.70
    POSITIVE LOGITS
     label
    0.94
     ports
    0.91
    label
    0.84
     interak
    0.79
    CardModule
    0.77
     selected
    0.77
     okaz
    0.77
    зидент
    0.75
    embedding
    0.75
    physics
    0.74
    Activations Density 0.010%

    No Known Activations