© 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. 102481
    Prev
    Next
    INDEX
    Explanations

    dependent sources

    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
     Éditions
    -0.86
     gadget
    -0.74
     Español
    -0.74
    keres
    -0.73
    Invitrogen
    -0.71
    hler
    -0.71
    축
    -0.71
    mö
    -0.70
    nowe
    -0.69
    minY
    -0.69
    POSITIVE LOGITS
    triangleq
    0.82
     IEEE
    0.81
    ソース
    0.80
    PlayerController
    0.75
    BOA
    0.74
     Beverage
    0.73
    phas
    0.73
     Permeability
    0.73
     cuentos
    0.72
     Conductor
    0.72
    Activations Density 0.008%

    No Known Activations