© 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. 34-GEMMASCOPE-RES-131K
    7. 83341
    Prev
    Next
    INDEX
    Explanations

    quantities equal to or compared with others

    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
     prieten
    -1.08
     entrambi
    -1.05
     []:
    -1.02
     diferite
    -1.02
    Which
    -0.99
     diferentes
    -0.97
     більш
    -0.97
    专属
    -0.96
     뉴스
    -0.96
     drept
    -0.95
    POSITIVE LOGITS
     twice
    2.08
     the
    2.03
    twice
    1.86
    Twice
    1.38
     half
    1.37
     thrice
    1.33
     Twice
    1.30
     whatever
    1.27
     TWICE
    1.21
    half
    1.16
    Activations Density 0.107%

    No Known Activations