© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74030
    Prev
    Next
    INDEX
    Explanations

    comprising parts and components

    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
     and
    -1.43
    𓋼
    -1.40
     chances
    -1.35
    + 
    -1.34
     totals
    -1.34
    蓥
    -1.32
    zheim
    -1.31
    тельных
    -1.30
    𝟵
    -1.30
     зве
    -1.30
    POSITIVE LOGITS
     kuhusu
    1.43
     noqa
    1.36
    Sì
    1.34
     sytuacji
    1.34
     appartient
    1.34
    źródło
    1.33
    didn
    1.31
     essentiellement
    1.30
     駅前
    1.30
    Tä
    1.30
    Activations Density 0.032%

    No Known Activations