© 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. 57235
    Prev
    Next
    INDEX
    Explanations

    blocks, states, sports, tech search

    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
     surprising
    -0.81
    اسي
    -0.77
     surprised
    -0.74
     sores
    -0.74
    ോ
    -0.73
    觥
    -0.73
     could
    -0.73
     prompted
    -0.72
     choosing
    -0.72
    بوع
    -0.72
    POSITIVE LOGITS
     Blocks
    0.97
     blocks
    0.97
     bloques
    0.89
    blocks
    0.86
     свет
    0.86
     Block
    0.84
    Block
    0.82
     block
    0.81
    Blocks
    0.80
    kait
    0.79
    Activations Density 0.010%

    No Known Activations