© 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. 84111
    Prev
    Next
    INDEX
    Explanations

    unanimous votes and decisions

    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
    บ้าง
    -0.79
    రు
    -0.77
    āci
    -0.73
    щей
    -0.73
     Україн
    -0.73
    linalg
    -0.71
     cancellations
    -0.71
    باء
    -0.71
     OnEnable
    -0.68
     prunes
    -0.68
    POSITIVE LOGITS
     unanimous
    5.56
     unanimously
    5.41
     unanim
    3.48
     consensus
    2.64
    animous
    2.36
    consensus
    2.16
     voted
    2.05
     едино
    2.05
     vote
    2.05
     votes
    2.05
    Activations Density 0.074%

    No Known Activations