© 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. 73884
    Prev
    Next
    INDEX
    Explanations

    classified into types

    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
     and
    -1.71
     this
    -1.21
     AND
    -1.06
     to
    -1.05
     M
    -1.04
     at
    -1.02
     Is
    -1.00
     intentó
    -1.00
     from
    -1.00
     Me
    -0.99
    POSITIVE LOGITS
     ortop
    1.17
     sonda
    1.13
     ortodo
    1.09
     vana
    1.08
     amma
    1.07
     imun
    1.06
     maky
    1.06
     drau
    1.06
     lant
    1.05
     valentino
    1.05
    Activations Density 0.115%

    No Known Activations