© 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. 91852
    Prev
    Next
    INDEX
    Explanations

    showing visuals

    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
    gráficos
    -1.07
    sweise
    -0.95
    eches
    -0.91
     dépenses
    -0.86
    scienced
    -0.85
    isticated
    -0.84
    UNICIP
    -0.82
     subclass
    -0.81
     sitesinde
    -0.81
     Screening
    -0.80
    POSITIVE LOGITS
     shots
    1.83
     comparison
    1.77
     closeup
    1.66
     close
    1.62
     showing
    1.61
     shot
    1.51
     zoomed
    1.45
     closer
    1.35
    比較
    1.34
     before
    1.31
    Activations Density 0.044%

    No Known Activations