© 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. 10-GEMMASCOPE-RES-131K
    4. 12325
    Prev
    Next
    INDEX
    Explanations

    sequencing and ordinals

    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_10/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
     superbes
    -1.65
     sportifs
    -1.64
     poignée
    -1.55
     zapato
    -1.54
     ouverture
    -1.53
    
    -1.51
     borracha
    -1.50
    ハンバーグ
    -1.49
     ранее
    -1.48
     ochi
    -1.46
    POSITIVE LOGITS
     on
    2.14
     to
    2.11
     in
    1.95
     t
    1.74
     into
    1.73
    </h1>
    1.73
    .”
    1.73
     porque
    1.68
    </h2>
    1.62
     f
    1.54
    Activations Density 0.015%

    No Known Activations