© 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. 26516
    Prev
    Next
    INDEX
    Explanations

    extremophile life in harsh environments

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

    life around hydrothermal vents

    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
    歼
    0.48
     آموزشی
    0.45
    发展
    0.43
    两人
    0.43
     granularity
    0.43
    战争
    0.41
    機械
    0.41
    Royce
    0.41
    掊
    0.41
    竞赛
    0.41
    POSITIVE LOGITS
     sulfide
    0.77
     sulfides
    0.73
     sulphide
    0.69
     sulfur
    0.68
     hydrothermal
    0.63
     geothermal
    0.62
     methane
    0.60
     seep
    0.59
     sulph
    0.59
     geochemical
    0.59
    Activations Density 0.031%

    No Known Activations