© 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. 58584
    Prev
    Next
    INDEX
    Explanations

    core, heart, basis, skeleton

    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
    kontak
    -0.90
     profumo
    -0.84
    embang
    -0.84
     tramonto
    -0.83
     lamenta
    -0.77
     sapore
    -0.76
    𝕙
    -0.76
     paesaggio
    -0.75
     polvere
    -0.74
    gelang
    -0.74
    POSITIVE LOGITS
     core
    5.97
    core
    4.19
     cores
    3.97
    Core
    3.73
     Core
    3.72
    核心
    3.69
    CORE
    3.41
     CORE
    3.39
    コア
    2.95
    cores
    2.81
    Activations Density 0.105%

    No Known Activations