© 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. 33751
    Prev
    Next
    INDEX
    Explanations

    pandas, groupby, drop, concatenate

    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
     TLC
    -0.85
    rali
    -0.84
    Converter
    -0.81
    uttg
    -0.80
     Harg
    -0.79
    TLC
    -0.76
     Keep
    -0.75
     even
    -0.75
     set
    -0.74
    >>();
    -0.74
    POSITIVE LOGITS
    셜
    0.78
     quadrangle
    0.77
     tween
    0.77
     RIT
    0.77
     pct
    0.77
    joined
    0.74
    comparing
    0.74
    μπ
    0.73
     intercom
    0.71
    belum
    0.71
    Activations Density 0.022%

    No Known Activations