© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103390
    Prev
    Next
    INDEX
    Explanations

    programming constructs

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

    the dollar sign ($) in PHP code, particularly when it appears at the beginning of variable declarations.

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

    This neuron activates on the PHP dollar‐sign token ( “$” ), i.e. it detects variable identifiers.

    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
     and
    -1.98
     continúas
    -1.91
     ogrom
    -1.69
     '
    -1.68
    其他
    -1.59
     "
    -1.59
    ,
    -1.59
     triko
    -1.57
     sezonu
    -1.55
     AMAZING
    -1.53
    POSITIVE LOGITS
    >
    1.59
    ↵↵
    1.48
     caoutchouc
    1.46
     carbone
    1.45
    UnifiedTopology
    1.44
     rhein
    1.41
     AGRIC
    1.41
     bumi
    1.41
     fulfil
    1.40
    参考にして
    1.38
    Activations Density 0.010%

    No Known Activations