© 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. 7093
    Prev
    Next
    INDEX
    Explanations

    groups and individuals

    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
     distances
    -0.82
     effects
    -0.81
    rens
    -0.80
     experiences
    -0.79
     events
    -0.79
     findings
    -0.78
    感受到
    -0.76
     tension
    -0.74
     vuitton
    -0.74
     escena
    -0.73
    POSITIVE LOGITS
     fellow
    1.15
     meaningful
    0.91
    members
    0.91
     NGOs
    0.89
     young
    0.88
     miembros
    0.86
     mlad
    0.84
     effortless
    0.84
     members
    0.84
     anggota
    0.82
    Activations Density 0.237%

    No Known Activations