© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116885
    Prev
    Next
    INDEX
    Explanations

    holding or arms

    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
    nmgp
    -0.80
    漬
    -0.74
    𝐫
    -0.72
     intégral
    -0.68
     OGSÅ
    -0.68
     polymerase
    -0.68
     Hình
    -0.67
     можуть
    -0.66
    bud
    -0.65
     nghiệm
    -0.65
    POSITIVE LOGITS
     arms
    5.44
    arms
    3.97
    Arms
    3.58
     Arms
    3.56
     brazos
    2.88
     ARMS
    2.83
     braços
    2.52
     braccia
    2.34
     arm
    2.13
     embrace
    2.11
    Activations Density 0.022%

    No Known Activations