© 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. 12455
    Prev
    Next
    INDEX
    Explanations

    language fragments and suffixes

    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
     में
    -1.34
    1
    -1.28
    ↵
    -1.27
    ureusement
    -1.23
    8
    -1.22
    2
    -1.20
    adhyay
    -1.19
    鍋
    -1.17
    を
    -1.16
    9
    -1.16
    POSITIVE LOGITS
     setDate
    1.35
    ﮦ
    1.33
     Nieuws
    1.28
    感じで
    1.24
    ところです
    1.23
    場所で
    1.23
    AGAIN
    1.21
    蔟
    1.21
     sorpresas
    1.21
     cinturón
    1.20
    Activations Density 0.002%

    No Known Activations