© 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. 93736
    Prev
    Next
    INDEX
    Explanations

    scientific citation keywords

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

    citation references in academic or scientific documents.

    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
    /**/*.
    -0.87
    inaudible
    -0.82
     "
    -0.82
     credits
    -0.78
     receita
    -0.77
    ..."
    -0.76
     [...]
    -0.75
     partner
    -0.75
    ),
    -0.74
     credit
    -0.74
    POSITIVE LOGITS
    ÓW
    0.96
    Prí
    0.93
    Ronald
    0.90
    ழ்
    0.88
    Tapi
    0.87
     Ronald
    0.86
     Ethan
    0.85
     pierres
    0.85
    Leon
    0.83
    ᅵ
    0.83
    Activations Density 0.001%

    No Known Activations