© 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. 70321
    Prev
    Next
    INDEX
    Explanations

    code includes and data structures

    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
    masi
    -0.81
    delion
    -0.76
     Temp
    -0.74
     UInt
    -0.73
     Resources
    -0.73
    wikk
    -0.71
    évolution
    -0.71
    Tuesday
    -0.71
     Troy
    -0.71
     Mediterranean
    -0.70
    POSITIVE LOGITS
     job
    1.13
    𝔢
    0.89
    android
    0.79
    flask
    0.75
    jvm
    0.74
     Java
    0.74
     Rimini
    0.74
    biography
    0.73
     java
    0.69
     emis
    0.68
    Activations Density 0.011%

    No Known Activations