© 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. 39754
    Prev
    Next
    INDEX
    Explanations

    opening code blocks or descriptions

    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
     falle
    -1.28
     procha
    -1.22
    moderne
    -1.15
    AxisSize
    -1.11
     kado
    -1.09
     nettoy
    -1.08
     prenn
    -1.08
    拉着
    -1.08
     etui
    -1.06
     Lunes
    -1.05
    POSITIVE LOGITS
     aptly
    1.21
     into
    1.21
     pointy
    1.16
    1.16
     two
    1.09
     without
    1.08
    fører
    1.05
     undeniably
    1.03
     Going
    1.02
     through
    1.02
    Activations Density 0.000%
    No Known Activations