© 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. 5732
    Prev
    Next
    INDEX
    Explanations

    geology and time periods

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

    geological features

    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
    multiSelectList
    0.95
    秘书
    0.93
     اداکار
    0.91
    批评
    0.89
     satış
    0.89
     ServicePolicy
    0.88
    帼
    0.88
    营收
    0.88
    钱包
    0.87
    嫔
    0.87
    POSITIVE LOGITS
     geologic
    1.77
     geological
    1.73
     geology
    1.69
     sedimentary
    1.63
     outcrop
    1.62
     outcrops
    1.59
     igneous
    1.47
     geochemical
    1.45
     sediment
    1.36
     groundwater
    1.35
    Activations Density 0.106%

    No Known Activations