© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73463
    Prev
    Next
    INDEX
    Explanations

    occasional some

    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
     in
    -1.05
    arraycopy
    -1.01
    gation
    -1.00
     volant
    -0.96
     listings
    -0.95
    gmail
    -0.93
     &=&
    -0.91
     туры
    -0.91
    жде
    -0.88
     apie
    -0.88
    POSITIVE LOGITS
     certaines
    1.38
     occasionally
    1.33
     jednotliv
    1.29
     niektor
    1.28
     occasional
    1.27
     někter
    1.23
     nových
    1.22
     algunas
    1.21
     poszczegól
    1.21
     Algunas
    1.20
    Activations Density 0.092%

    No Known Activations