© 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. 12720
    Prev
    Next
    INDEX
    Explanations

    programming code and errors

    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
    づけ
    -1.30
     their
    -1.30
    珦
    -1.30
     Some
    -1.27
     Remember
    -1.23
    ⌗
    -1.23
     for
    -1.20
    ślę
    -1.19
    ⃨
    -1.14
     politiet
    -1.13
    POSITIVE LOGITS
    <bos>
    1.53
    ↵
    1.19
     WaitForSeconds
    1.09
    は
    1.02
     monumental
    1.01
     jPanel
    1.01
    ที่มี
    1.01
    ตรี
    1.01
    owano
    0.98
    0.98
    Activations Density 0.000%
    No Known Activations