© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99735
    Prev
    Next
    INDEX
    Explanations

    molecular physics and chemistry

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

    scientific terms related to molecular and atomic structures in academic 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_10/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
     horrible
    -1.27
    你不要
    -1.25
     mesma
    -1.25
    方がいい
    -1.23
     alcune
    -1.21
    국의
    -1.18
     bè
    -1.18
    Specific
    -1.17
     superb
    -1.16
     granada
    -1.16
    POSITIVE LOGITS
     longstanding
    1.35
     Before
    1.35
     Since
    1.32
    ddb
    1.24
     before
    1.22
     only
    1.22
     Shortly
    1.22
     since
    1.21
     AND
    1.20
     first
    1.19
    Activations Density 0.090%

    No Known Activations