© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91979
    Prev
    Next
    INDEX
    Explanations

    Judge opinions

    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
    bps
    -0.75
    ütter
    -0.73
    ITEM
    -0.73
     фур
    -0.71
    batch
    -0.71
    RAM
    -0.69
    STICK
    -0.69
    trieb
    -0.68
    bout
    -0.68
     Brus
    -0.67
    POSITIVE LOGITS
    homePage
    0.74
     paire
    0.73
     Kremlin
    0.73
    妪
    0.70
    φή
    0.69
     Empathy
    0.68
     nữa
    0.68
    throwaway
    0.66
     sonder
    0.66
     ended
    0.66
    Activations Density 0.047%

    No Known Activations