© 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. 118446
    Prev
    Next
    INDEX
    Explanations

    issue labels

    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
     Вт
    -0.73
    략
    -0.72
    паковка
    -0.69
    }/{
    -0.68
     ó
    -0.67
     Depp
    -0.66
    浓
    -0.66
     문
    -0.66
     acknowledgement
    -0.66
    bd
    -0.65
    POSITIVE LOGITS
    Labels
    1.21
     labels
    1.12
    labels
    1.12
     Labels
    1.10
    issue
    1.07
    Issue
    1.04
    ラベル
    1.02
    Label
    1.01
     label
    0.93
     LABEL
    0.91
    Activations Density 0.030%

    No Known Activations