© 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. 101680
    Prev
    Next
    INDEX
    Explanations

    constructor initializations

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

    variable or attribute assignments in code, particularly when initializing object properties.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires strongly on identifiers used as object or class field names—especially the variable names assigned to “this.” or “self.” in constructors or initializers.

    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
     juntamente
    -1.89
     of
    -1.63
     valamint
    -1.59
     Ahora
    -1.52
    PullParser
    -1.47
     and
    -1.46
     influenci
    -1.44
    commodation
    -1.41
     along
    -1.38
    irmanship
    -1.38
    POSITIVE LOGITS
    </h2>
    1.66
    .
    1.60
    }
    1.50
    e
    1.43
     själva
    1.34
    return
    1.27
    是
    1.23
    Unlike
    1.21
     fortfarande
    1.20
    kunst
    1.20
    Activations Density 0.011%

    No Known Activations