© 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. 68717
    Prev
    Next
    INDEX
    Explanations

    deduct, deductions, deductible

    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
    </strong>
    -2.89
    -2.56
     This
    -2.27
     Luckily
    -2.06
    en
    -1.96
     입니다
    -1.95
    All
    -1.94
     –
    -1.94
    新的
    -1.92
     Its
    -1.91
    POSITIVE LOGITS
    瘣
    2.61
    medriver
    2.50
    狆
    2.34
     respald
    2.27
     escuchadas
    2.27
     prácticamente
    2.20
     soñ
    2.20
     supuestamente
    2.20
     enmar
    2.13
     básicamente
    2.11
    Activations Density 0.009%

    No Known Activations