© 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. 30581
    Prev
    Next
    INDEX
    Explanations

    scientific methods and properties

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

    scientific or technical terms related to methods, properties, or effects in research papers.

    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
     or
    -1.48
     after
    -1.44
     because
    -1.38
     four
    -1.38
     two
    -1.38
     three
    -1.35
     nine
    -1.30
     this
    -1.29
     time
    -1.28
     most
    -1.27
    POSITIVE LOGITS
     SUCH
    1.30
     которые
    1.21
     such
    1.18
     XVII
    1.13
     takimi
    1.06
    idk
    1.05
    donc
    1.05
    llac
    1.04
     LITER
    1.02
     nô
    1.02
    Activations Density 0.329%

    No Known Activations