© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11554
    Prev
    Next
    INDEX
    Explanations

    average or sum

    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_22/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
    olkien
    -0.87
     everything
    -0.87
    everything
    -0.84
    馒
    -0.83
     tudo
    -0.82
     स्व
    -0.81
    entennial
    -0.81
     KPMG
    -0.80
     رک
    -0.79
    entamiento
    -0.78
    POSITIVE LOGITS
     average
    1.39
     averaged
    1.24
     only
    1.24
     averages
    1.20
    Average
    1.17
     averaging
    1.13
    平均
    1.07
    average
    1.05
     representative
    1.05
    sum
    1.04
    Activations Density 0.101%

    No Known Activations