© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 48336
    Prev
    Next
    INDEX
    Explanations

    x-ray analysis and techniques

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

    terms related to X-ray technology in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects mentions of “X-ray” (i.e. the token “ray” in “X-ray”) in descriptions of analytical or imaging methods.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ㋛
    -2.50
    (
    -2.38
    ).
    -2.33
    of
    -2.25
    ของ
    -2.19
    +="
    -2.14
     Saltar
    -2.14
    #
    -2.13
    </sup>
    -2.02
    醗
    -1.98
    POSITIVE LOGITS
     iſt
    2.36
    蓴
    2.25
     sogen
    2.23
     sabias
    2.17
     preciosas
    2.14
    葙
    2.14
     maravillosas
    2.11
     successes
    2.11
     antiguas
    2.09
    </h3>
    2.02
    Activations Density 0.015%

    No Known Activations