© 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. 22-GEMMASCOPE-RES-131K
    7. 10843
    Prev
    Next
    INDEX
    Explanations

    past events and future possibilities

    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_22/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
     چیست
    -1.75
    springen
    -1.52
     dokter
    -1.48
    förm
    -1.48
    glück
    -1.45
     kämp
    -1.41
     anser
    -1.41
     Ministre
    -1.41
     帅气
    -1.38
     Dokter
    -1.38
    POSITIVE LOGITS
     didn
    2.48
     same
    2.19
     couldn
    2.11
     still
    2.09
     got
    1.94
     biggest
    1.88
     could
    1.88
     haven
    1.87
     not
    1.85
     actually
    1.84
    Activations Density 0.078%

    No Known Activations