© 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. 120040
    Prev
    Next
    INDEX
    Explanations

    winning symbols and descriptions

    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
    )
    
    -1.31
    quelize
    -1.31
    </strong>
    -1.26
    createDate
    -1.23
     extranjera
    -1.20
     حدود
    -1.19
     ベクトル
    -1.19
    擤
    -1.17
     Schwierigkeiten
    -1.16
    </u>
    -1.16
    POSITIVE LOGITS
     all
    1.72
     creía
    1.41
     verhind
    1.36
     ouvrages
    1.36
    ingat
    1.34
     duradero
    1.34
     gouden
    1.34
     zeven
    1.30
     waarop
    1.30
    resting
    1.28
    Activations Density 0.012%

    No Known Activations