© 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. 66176
    Prev
    Next
    INDEX
    Explanations

    causing damage or collapse

    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
     to
    -1.34
     for
    -0.96
     для
    -0.95
     maneiras
    -0.94
    ání
    -0.88
    ポチ
    -0.84
     zelfs
    -0.84
     será
    -0.84
    被打
    -0.82
     if
    -0.81
    POSITIVE LOGITS
     causing
    2.31
     sending
    2.28
     send
    1.80
    sending
    1.77
     Sending
    1.63
    causing
    1.62
    Sending
    1.60
     sends
    1.57
     resulting
    1.54
     forcing
    1.48
    Activations Density 0.076%

    No Known Activations