© 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. 28053
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
     moletom
    -1.12
     gän
    -1.09
    ͗
    -1.06
     diesmal
    -1.05
    বং
    -1.02
     boneca
    -1.00
     gänzlich
    -1.00
     popolo
    -1.00
     caminhada
    -1.00
    各类
    -0.99
    POSITIVE LOGITS
     from
    1.16
     है
    1.05
    </i>
    1.03
     that
    1.02
     only
    0.97
     Lê
    0.96
     gewoon
    0.94
    förmig
    0.91
     abusi
    0.91
     infeksi
    0.91
    Activations Density 0.012%

    No Known Activations