© 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. 2676
    Prev
    Next
    INDEX
    Explanations

    Chamber, American, AP, Q

    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
    dö
    -0.84
    Mig
    -0.77
    ález
    -0.76
     колеса
    -0.76
    mig
    -0.76
    김
    -0.75
    Fourier
    -0.73
    ServiceProvider
    -0.72
     Undeclared
    -0.72
    灭
    -0.72
    POSITIVE LOGITS
     chamber
    1.10
    Cham
    1.07
     chambers
    1.02
     Am
    0.95
    CHAM
    0.93
     Chamber
    0.92
    Chamber
    0.88
     business
    0.85
     American
    0.84
    chamber
    0.82
    Activations Density 0.015%

    No Known Activations