© 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. 81655
    Prev
    Next
    INDEX
    Explanations

    worth it

    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
    懷
    -0.93
     hardly
    -0.88
     Gauge
    -0.79
    дото
    -0.78
    クション
    -0.77
     Dü
    -0.73
    hdl
    -0.73
    Kube
    -0.73
    jemy
    -0.73
     李
    -0.71
    POSITIVE LOGITS
     pena
    1.05
     moeite
    1.02
     stojí
    1.02
     effort
    0.93
     worth
    0.92
     оно
    0.89
     того
    0.86
     mentioning
    0.85
    alinga
    0.81
    価値
    0.79
    Activations Density 0.008%

    No Known Activations