© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21395
    Prev
    Next
    INDEX
    Explanations

    DSL, DSLR, NAS, Young

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

    This neuron activates on occurrences of “DSL” (in any casing) in the text.

    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
    谖
    -2.86
    鹋
    -2.66
    鉺
    -2.61
    呖
    -2.59
    
    -2.58
    潆
    -2.56
    熥
    -2.42
    趼
    -2.42
    UGHTER
    -2.36
    踅
    -2.36
    POSITIVE LOGITS
    A
    3.11
    \
    2.66
    y
    2.41
    D
    2.20
    www
    2.20
    да
    2.19
     genaue
    2.14
    “
    2.13
    s
    2.11
    *
    2.09
    Activations Density 0.001%

    No Known Activations