© 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. 59044
    Prev
    Next
    INDEX
    Explanations

    computed columns

    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
    dataclass
    -0.80
    fasis
    -0.77
    liceerd
    -0.75
    voř
    -0.74
    banez
    -0.73
    ghal
    -0.73
    IFont
    -0.72
    umentar
    -0.72
    faat
    -0.72
    nejšie
    -0.72
    POSITIVE LOGITS
     computed
    3.27
     calculated
    3.16
     derived
    2.92
    computed
    2.69
    Computed
    2.56
    calculated
    2.48
    Derived
    2.47
    Calculated
    2.44
     Calculated
    2.44
    derived
    2.39
    Activations Density 0.089%

    No Known Activations