© 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. 84910
    Prev
    Next
    INDEX
    Explanations

    do not edit

    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
     destina
    -0.87
    струкция
    -0.77
     monstru
    -0.77
    default
    -0.77
     alde
    -0.76
    友人
    -0.75
    Zgod
    -0.74
     дав
    -0.73
    夫婦
    -0.73
     esper
    -0.73
    POSITIVE LOGITS
    colleg
    1.02
     shouldn
    0.91
    upvote
    0.88
    yamaha
    0.87
    omyelitis
    0.85
     overridden
    0.80
     AVOID
    0.80
    encu
    0.79
    郴
    0.78
     peligroso
    0.77
    Activations Density 0.004%

    No Known Activations