© 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. 66605
    Prev
    Next
    INDEX
    Explanations

    court cases, numbers, dates

    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
     idyl
    -1.28
     visuel
    -1.27
     virtuelle
    -1.25
     fuis
    -1.18
     zove
    -1.16
     lej
    -1.16
     milliard
    -1.15
     marka
    -1.14
     guir
    -1.13
     tirs
    -1.12
    POSITIVE LOGITS
     will
    1.06
     and
    1.02
     know
    0.98
     Geschäft
    0.97
     northwestern
    0.97
     cuyas
    0.97
     każde
    0.94
    向了
    0.94
     conductas
    0.94
     T
    0.93
    Activations Density 0.005%

    No Known Activations