© 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. 115493
    Prev
    Next
    INDEX
    Explanations

    attorney at law

    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
     چوبی
    -1.02
     podem
    -0.97
    これに
    -0.96
    合わせた
    -0.92
    זיה
    -0.89
    esar
    -0.85
    嚒
    -0.85
     alright
    -0.84
    vantaged
    -0.83
    Xf
    -0.82
    POSITIVE LOGITS
     fees
    1.44
     specializing
    1.14
     representing
    1.14
    fees
    1.13
     FEES
    1.12
     Fees
    1.04
     representar
    1.03
    urally
    1.02
     attorney
    1.01
     representation
    0.99
    Activations Density 0.028%

    No Known Activations