© 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. 99010
    Prev
    Next
    INDEX
    Explanations

    the key

    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
    onal
    -0.88
    even
    -0.73
    hir
    -0.72
    ional
    -0.71
     Stop
    -0.71
    eller
    -0.70
    she
    -0.70
    Stop
    -0.70
     Till
    -0.69
    iz
    -0.69
    POSITIVE LOGITS
     Kön
    0.83
    woofer
    0.82
     理
    0.82
    Fry
    0.81
     configurações
    0.79
     bohat
    0.78
    UTION
    0.77
    stiker
    0.77
    ház
    0.76
     CoreData
    0.76
    Activations Density 0.016%

    No Known Activations