© 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. 34-GEMMASCOPE-RES-131K
    4. 73351
    Prev
    Next
    INDEX
    Explanations

    target

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

    This neuron responds to occurrences of the word “target” (in any casing or as part of identifiers and file-path components).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ши
    -0.87
     gelen
    -0.87
     Geraadpleegd
    -0.85
     Spatial
    -0.85
     servitude
    -0.84
    📓
    -0.83
     individuel
    -0.82
     salão
    -0.82
    rification
    -0.81
     =-\
    -0.81
    POSITIVE LOGITS
     targ
    0.93
     target
    0.87
    älte
    0.80
     targets
    0.79
    target
    0.79
     Segel
    0.76
    gias
    0.76
    tar
    0.76
     عالم
    0.71
     getTarget
    0.70
    Activations Density 0.044%

    No Known Activations