© 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. 71037
    Prev
    Next
    INDEX
    Explanations

    termination value or financial clauses

    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
     πρ
    -1.60
    Kindly
    -1.40
     loh
    -1.34
     lauk
    -1.34
     our
    -1.31
     οὐ
    -1.28
     bijoux
    -1.24
     koe
    -1.23
     toki
    -1.23
    為に
    -1.20
    POSITIVE LOGITS
     or
    1.71
     السياس
    1.60
    When
    1.45
    當
    1.38
    wyk
    1.31
     businesses
    1.30
    <tr>
    1.30
     matters
    1.29
     Obtén
    1.28
    﨑
    1.27
    Activations Density 0.005%

    No Known Activations