© 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. 107375
    Prev
    Next
    INDEX
    Explanations

    past experiences

    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
     appena
    -1.04
    İY
    -1.01
    minos
    -0.96
    addington
    -0.94
    任何
    -0.88
    diseases
    -0.88
    始めた
    -0.86
    nende
    -0.84
    сник
    -0.83
    bidities
    -0.83
    POSITIVE LOGITS
     previously
    1.34
     experience
    1.32
    เคย
    1.30
     từng
    1.15
     never
    1.13
    做过
    1.12
     done
    1.12
     pernah
    1.11
    有过
    1.08
     durchaus
    1.05
    Activations Density 0.055%

    No Known Activations