© 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. 104870
    Prev
    Next
    INDEX
    Explanations

    ObjC, Obj, JS Object

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

    the token "Obj" in programming code, particularly in variable names and object declarations.

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

    The neuron fires on occurrences of the token “Obj,” i.e. references to object or class names containing “Obj” in code.

    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
    逦
    -3.38
    龊
    -3.34
    ſelves
    -3.13
     letzten
    -2.70
    拮
    -2.63
    狁
    -2.61
    鲀
    -2.58
    ondheim
    -2.58
    骓
    -2.53
     großen
    -2.45
    POSITIVE LOGITS
    \
    3.31
    "
    3.31
     The
    3.17
    1
    2.98
    4
    2.84
    6
    2.70
    い
    2.67
    {
    2.63
    re
    2.61
     they
    2.61
    Activations Density 0.002%

    No Known Activations