© 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. 92214
    Prev
    Next
    INDEX
    Explanations

    working or completed actions

    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
     your
    -1.34
     you
    -1.23
    mishes
    -1.23
     хочется
    -1.06
    和你
    -1.05
    ）：
    -1.03
     freno
    -1.02
    Chú
    -1.02
     melh
    -1.01
     IMHO
    -0.97
    POSITIVE LOGITS
     would
    1.88
     pihaknya
    1.68
     "
    1.52
     because
    1.52
     “
    1.45
     könne
    1.29
     but
    1.27
     habían
    1.27
     blah
    1.22
     agricultores
    1.21
    Activations Density 0.041%

    No Known Activations