© 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. 104422
    Prev
    Next
    INDEX
    Explanations

    not even

    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
     ekolog
    -1.14
     echter
    -1.05
     élas
    -1.04
     konkre
    -1.04
     gorro
    -1.02
    𝐊
    -1.02
     aranha
    -0.98
     falda
    -0.98
     suéter
    -0.96
     comportements
    -0.95
    POSITIVE LOGITS
     also
    2.06
     even
    1.97
     даже
    1.79
     tampoco
    1.67
     też
    1.51
     نیز
    1.37
     too
    1.32
    Even
    1.28
    even
    1.27
    いても
    1.26
    Activations Density 0.058%

    No Known Activations