© 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. 30551
    Prev
    Next
    INDEX
    Explanations

    integration of disparate elements

    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
    وبر
    -1.12
     when
    -1.02
     including
    -1.00
    varer
    -0.96
    Each
    -0.96
    之一
    -0.94
    どちらも
    -0.94
    just
    -0.94
     on
    -0.93
     or
    -0.93
    POSITIVE LOGITS
     disparate
    3.02
     different
    1.94
     différents
    1.84
     scattered
    1.78
     verschillende
    1.74
     fragmented
    1.73
     différentes
    1.68
    different
    1.54
     distintos
    1.54
     separate
    1.51
    Activations Density 0.091%

    No Known Activations