© 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. 70459
    Prev
    Next
    INDEX
    Explanations

    purpose or consequence

    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
     during
    -1.07
     while
    -1.03
    しては
    -0.96
    前は
    -0.93
     usually
    -0.93
    中でも
    -0.91
     using
    -0.91
    butuhkan
    -0.91
    いたします
    -0.90
     mépris
    -0.90
    POSITIVE LOGITS
    (#
    1.16
     possib
    1.13
     then
    1.12
     borboleta
    1.06
    以便
    1.06
    ViewInit
    1.05
    能够
    1.05
     supaya
    1.05
     étant
    1.02
     pourra
    1.02
    Activations Density 0.035%

    No Known Activations