© 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. 39974
    Prev
    Next
    INDEX
    Explanations

    code setup and licensing

    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
    ノリ
    -1.21
     яго
    -1.12
    けどね
    -1.11
    って思
    -1.10
    ebly
    -1.05
     stycznia
    -1.04
    Kemudian
    -1.02
    ゴリ
    -1.02
     bolster
    -1.02
     his
    -1.00
    POSITIVE LOGITS
     funciona
    1.23
    𝐩
    1.10
     speciale
    1.09
    ="
    1.06
     coloque
    1.06
     será
    1.05
     где
    1.04
    PIL
    1.01
    retten
    0.99
     😉
    0.98
    Activations Density 0.277%

    No Known Activations