© 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. 34-GEMMASCOPE-RES-131K
    7. 59564
    Prev
    Next
    INDEX
    Explanations

    ionic crystals and bonding

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

    terms related to solid state materials, crystals, and atomic/molecular structures.

    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
    onaceous
    -0.79
    rih
    -0.73
    köping
    -0.72
     oils
    -0.70
    发动
    -0.69
    bottomrule
    -0.68
     kw
    -0.68
     desired
    -0.68
     Belts
    -0.68
    elyk
    -0.67
    POSITIVE LOGITS
     lattice
    1.15
     ionic
    1.15
    Lattice
    1.02
     crystal
    1.02
     Lattice
    0.99
    NaCl
    0.97
    lattice
    0.95
    Ionic
    0.95
     Ionic
    0.94
     bonding
    0.92
    Activations Density 0.017%

    No Known Activations