© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98251
    Prev
    Next
    INDEX
    Explanations

    discovery and identification

    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
    tablir
    -0.82
    réhen
    -0.76
    BER
    -0.75
    볼
    -0.75
    šan
    -0.74
    ariConfig
    -0.73
    銨
    -0.72
    看不到
    -0.71
    jaer
    -0.70
     dinilai
    -0.70
    POSITIVE LOGITS
     discovery
    7.13
     discovered
    6.66
     discover
    6.09
    discovery
    5.81
     discoveries
    5.78
     discovering
    5.53
    discover
    5.44
    discovered
    5.31
     discovers
    5.28
    Discovery
    5.19
    Activations Density 0.320%

    No Known Activations