© 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. 57351
    Prev
    Next
    INDEX
    Explanations

    daily newsletter

    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
    UpdateData
    -0.75
    (/*
    -0.74
    渔
    -0.74
    🖨
    -0.73
    互動
    -0.73
    Tide
    -0.71
     almost
    -0.70
     pharmaco
    -0.70
     archiving
    -0.69
     Computation
    -0.68
    POSITIVE LOGITS
    maier
    0.79
     Clean
    0.77
    ës
    0.75
     Balkan
    0.74
     BigInt
    0.73
    (',')
    0.73
     BaseController
    0.72
    rshire
    0.72
    OTA
    0.71
    EndInit
    0.71
    Activations Density 0.016%

    No Known Activations