© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48772
    Prev
    Next
    INDEX
    Explanations

    octopus

    np_acts-logits-general · gemini-2.5-flash-lite

    code blocks or programming-related content in various languages.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     both
    -0.84
    {}/
    -0.80
    ȴ
    -0.78
    ********/
    -0.77
     fled
    -0.75
    interceptors
    -0.74
     bevestig
    -0.72
    vesti
    -0.71
     even
    -0.71
     through
    -0.71
    POSITIVE LOGITS
     jol
    1.05
     basins
    1.02
    Risk
    0.94
    risk
    0.89
     basin
    0.88
     adapters
    0.86
    Adapter
    0.85
    forward
    0.84
     Basin
    0.84
    Expense
    0.82
    Activations Density 0.006%

    No Known Activations