© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39168
    Prev
    Next
    INDEX
    Explanations

    plus bevacizumab, / Graphene, + thalidomide, and Z250, plus auricular, + couchette, plus low-dose, / SrIrO3, /hydrogel, + INDEX

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

    symbols, conjunctions, and relationships between components, particularly focusing on the "/" symbol and terms connected with "plus" and "and".

    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
     многих
    -1.15
     contrôler
    -1.15
     apprécier
    -1.09
     participer
    -1.09
     favoriser
    -1.09
    はかなり
    -1.09
     GETTING
    -1.08
    誂
    -1.08
     grâce
    -1.07
    despite
    -1.07
    POSITIVE LOGITS
     with
    1.68
     or
    1.61
     three
    1.46
     people
    1.39
     two
    1.37
     five
    1.36
     huge
    1.34
     an
    1.31
     changed
    1.30
     strong
    1.30
    Activations Density 0.152%

    No Known Activations