© 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. 116567
    Prev
    Next
    INDEX
    Explanations

    cases, citations, and legal documents

    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
     EPA
    -1.00
     //
    -0.88
     incl
    -0.85
     _
    -0.84
     بإ
    -0.79
     лимон
    -0.79
     F
    -0.79
    瀚
    -0.78
     его
    -0.78
     ३
    -0.77
    POSITIVE LOGITS
     réparer
    1.14
     полного
    1.11
    Olvid
    1.06
     combattre
    1.05
     plong
    1.02
     leggermente
    1.02
     grasas
    1.01
     bluz
    1.01
    Estar
    1.01
     rilass
    0.98
    Activations Density 0.001%

    No Known Activations