© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1213
    Prev
    Next
    INDEX
    Explanations

    water and its properties

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

    references to water bodies, including oceans, lakes, rivers, and marine environments.

    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_10/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
    which
    -1.66
    T
    -1.63
    if
    -1.59
    1
    -1.59
     then
    -1.54
    V
    -1.49
    Z
    -1.44
    頃から
    -1.43
    ats
    -1.41
    J
    -1.41
    POSITIVE LOGITS
     imbued
    1.42
     estudian
    1.41
     ".
    1.38
    ⎔
    1.36
     anteriormente
    1.36
    asticity
    1.34
    릭터
    1.34
    momix
    1.32
     protegida
    1.32
     denominada
    1.31
    Activations Density 0.025%

    No Known Activations