© 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. 22-GEMMASCOPE-RES-131K
    7. 15295
    Prev
    Next
    INDEX
    Explanations

    in vitro experiments

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

    The phrase "in vitro" which refers to experiments performed in a controlled laboratory environment outside of living organisms.

    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_22/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
    
    -2.25
    辚
    -2.14
    姈
    -2.05
     ‘‘
    -2.05
    憮
    -2.03
    玙
    -2.03
    盦
    -2.03
    
    -2.00
    珰
    -2.00
    おわりに
    -2.00
    POSITIVE LOGITS
     '
    1.84
    '
    1.70
     "
    1.70
    ?"
    1.69
     作り方
    1.61
    ...
    1.54
    ..."
    1.52
    </sup>
    1.52
    ...."
    1.52
    </em>
    1.48
    Activations Density 0.055%

    No Known Activations