© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77426
    Prev
    Next
    INDEX
    Explanations

    IIM, MBA, Booking, Mille Lacs

    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
    รง
    -0.83
     记
    -0.77
    dropna
    -0.77
     londres
    -0.77
    ★★★
    -0.76
     ɛ
    -0.75
    ዘ
    -0.75
    ბ
    -0.73
     Nx
    -0.73
     NIOS
    -0.72
    POSITIVE LOGITS
     PGP
    0.90
    pgp
    0.86
     Securities
    0.84
    CAT
    0.82
     MBA
    0.82
     CAT
    0.80
     सम
    0.79
    Batch
    0.77
     wilderness
    0.77
     Marketing
    0.75
    Activations Density 0.005%

    No Known Activations