© 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. 47777
    Prev
    Next
    INDEX
    Explanations

    prepare for future events

    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
    𝒙
    -0.96
    部件
    -0.87
    átula
    -0.83
     reproducir
    -0.83
     encender
    -0.82
     bricolaje
    -0.82
     permanecer
    -0.82
    ınt
    -0.81
     cocinar
    -0.81
    nię
    -0.80
    POSITIVE LOGITS
     to
    2.05
     for
    1.95
     mentally
    1.16
     adequately
    1.05
     inför
    1.01
     accordingly
    1.00
    迎接
    0.99
    万一
    0.99
     ahead
    0.96
     psychologically
    0.93
    Activations Density 0.017%

    No Known Activations