© 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. 57237
    Prev
    Next
    INDEX
    Explanations

    Altered, Restricted to, 1 full

    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
     Really
    -0.91
    zku
    -0.88
     subtly
    -0.85
     initiating
    -0.84
     sophisticated
    -0.84
     съдържа
    -0.83
     compelling
    -0.83
     Having
    -0.81
     unparalleled
    -0.81
     helped
    -0.79
    POSITIVE LOGITS
    endance
    0.87
     Century
    0.85
     vários
    0.84
     predominantly
    0.81
    locked
    0.81
     masterful
    0.81
     actuellement
    0.81
     группа
    0.79
     alguns
    0.79
     exceptionally
    0.78
    Activations Density 0.000%

    No Known Activations