© 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. 69919
    Prev
    Next
    INDEX
    Explanations

    method calls and definitions

    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
     Utiliza
    -0.91
     камня
    -0.88
    ここでは
    -0.86
     bowing
    -0.85
     Leurs
    -0.85
    今まで
    -0.84
    コロナ
    -0.84
    memb
    -0.82
    verwaltung
    -0.81
     Lorsque
    -0.81
    POSITIVE LOGITS
     Get
    1.19
     String
    1.03
     set
    1.02
     get
    0.98
    Get
    0.95
    mphony
    0.90
    get
    0.88
     Is
    0.86
    vdots
    0.84
    (!__
    0.84
    Activations Density 0.003%

    No Known Activations