© 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. 34-GEMMASCOPE-RES-131K
    4. 90143
    Prev
    Next
    INDEX
    Explanations

    waive fees or loans

    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_34/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
     ventri
    -0.74
    cale
    -0.71
    addHandler
    -0.70
    conomie
    -0.67
    hosa
    -0.67
    ㅂ
    -0.67
     venn
    -0.66
    </caption>
    -0.66
    ớ
    -0.66
    suited
    -0.65
    POSITIVE LOGITS
     waived
    5.03
     waive
    4.91
     waiver
    4.34
     wa
    3.52
     Waiver
    3.41
     waivers
    3.38
     Wa
    3.06
    Wai
    2.88
    Wa
    2.72
    wa
    2.55
    Activations Density 0.061%

    No Known Activations