© 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. 78037
    Prev
    Next
    INDEX
    Explanations

    crystal structure and data

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

    references to crystal structures in scientific 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
     cheminée
    -0.93
     diecast
    -0.88
     amigurumi
    -0.88
    ër
    -0.86
     поможет
    -0.85
     hasbro
    -0.85
    Examen
    -0.84
     légère
    -0.83
    都在
    -0.83
     chibi
    -0.82
    POSITIVE LOGITS
    lographic
    1.20
     crystal
    1.19
     structure
    1.16
    crystal
    1.01
     violet
    1.01
    structure
    0.93
     Structure
    0.92
     STRUCTURE
    0.92
     Crystal
    0.89
    人人
    0.89
    Activations Density 0.022%

    No Known Activations