© 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. 54277
    Prev
    Next
    INDEX
    Explanations

    heron, ibis, egret, rook

    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
    zzleHttp
    -0.86
    pherds
    -0.82
    ILLO
    -0.82
     Approve
    -0.79
    万美元
    -0.75
    updating
    -0.73
    一開始
    -0.72
    ImagePath
    -0.72
    gler
    -0.72
     échelle
    -0.71
    POSITIVE LOGITS
     heron
    1.30
     ibis
    1.16
     Heron
    1.15
     egret
    1.05
     Eg
    1.05
     rook
    0.93
     Cattle
    0.88
     Hero
    0.87
     fishing
    0.87
     cattle
    0.85
    Activations Density 0.027%

    No Known Activations