© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2760
    Prev
    Next
    INDEX
    Explanations

    receive, transmit, read, write

    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
     inbound
    -0.96
     inversa
    -0.91
     sosi
    -0.88
    culada
    -0.86
     outbound
    -0.85
    OUTPUT
    -0.85
     撮影
    -0.84
     romero
    -0.82
     transmis
    -0.81
     inpatient
    -0.80
    POSITIVE LOGITS
     side
    0.95
    端的
    0.90
     Side
    0.85
    SIDE
    0.85
     buffer
    0.85
    side
    0.83
    seitig
    0.79
    enb
    0.79
    BufferSize
    0.79
    ])):
    0.79
    Activations Density 0.043%

    No Known Activations