© 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. 72966
    Prev
    Next
    INDEX
    Explanations

    numbers and code

    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
     that
    -1.24
     and
    -1.24
     like
    -1.13
     reduce
    -1.03
     but
    -1.02
     while
    -1.01
     one
    -1.00
     stylish
    -1.00
     big
    -0.99
    に行った
    -0.98
    POSITIVE LOGITS
    その
    1.26
    찻
    1.13
     soooo
    1.13
     sooo
    1.13
    UCIÓN
    1.12
     quay
    1.11
    çants
    1.09
     CGT
    1.09
    があり
    1.07
     répertoire
    1.07
    Activations Density 0.001%

    No Known Activations