© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40536
    Prev
    Next
    INDEX
    Explanations

    material properties and microscopy

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

    functional groups, porosity, and catalysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    制造
    0.45
    Ward
    0.44
    வெளி
    0.44
    細胞
    0.42
    硋
    0.42
    溦
    0.42
    লিখ
    0.42
    Ⅼ
    0.42
    🧬
    0.41
    يان
    0.41
    POSITIVE LOGITS
     adsorption
    0.52
     waterproofing
    0.52
     hydrophobic
    0.50
     waterproof
    0.49
     adsor
    0.48
     hydroph
    0.46
     Waterproof
    0.45
     peaks
    0.45
     imperme
    0.44
     hydrophilic
    0.43
    Activations Density 0.016%

    No Known Activations