© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 372
    Prev
    Next
    INDEX
    Explanations

    prepared, recorded, or set

    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
    nąć
    -0.94
     gouden
    -0.92
    िव
    -0.90
    Zac
    -0.90
    Seine
    -0.89
     tandis
    -0.88
     lorsqu
    -0.88
     уверен
    -0.88
    っとり
    -0.87
     jedem
    -0.86
    POSITIVE LOGITS
     during
    1.30
     earlier
    1.13
     this
    1.06
     into
    1.05
     вами
    1.02
     previously
    1.02
     any
    0.99
     recently
    0.98
     by
    0.98
     on
    0.97
    Activations Density 0.085%

    No Known Activations