© 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. 60619
    Prev
    Next
    INDEX
    Explanations

    qualifying an effect or impact

    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
    zestaw
    -0.91
    entyfik
    -0.88
    охра
    -0.87
     うどん
    -0.82
    paralleled
    -0.81
    Vaata
    -0.81
     CommandType
    -0.81
    matically
    -0.80
    ambassade
    -0.79
    Responding
    -0.79
    POSITIVE LOGITS
     effect
    4.50
     effects
    3.31
    effect
    3.30
     Effect
    2.80
    Effect
    2.75
    作用
    2.50
    効果
    2.41
    效果
    2.33
     efecto
    2.23
    effects
    2.23
    Activations Density 0.184%

    No Known Activations