© 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. 69955
    Prev
    Next
    INDEX
    Explanations

    description, factual reporting, advice

    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
    咂
    -1.00
    ruptcy
    -0.91
    言葉を
    -0.90
    saying
    -0.82
    spoke
    -0.82
    excellent
    -0.82
     eder
    -0.82
    ából
    -0.81
    說的
    -0.81
    跹
    -0.81
    POSITIVE LOGITS
     instructions
    1.59
     instruction
    1.39
     factual
    1.35
     Instructions
    1.34
     advice
    1.34
     informational
    1.32
     announcement
    1.31
     informative
    1.29
     information
    1.22
     description
    1.22
    Activations Density 0.079%

    No Known Activations