© 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. 22-GEMMASCOPE-RES-131K
    7. 36447
    Prev
    Next
    INDEX
    Explanations

    iterating over data structures

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

    This neuron detects PHP variable tokens (a dollar sign “$” introducing a variable name).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     kapak
    -1.51
     kredi
    -1.50
     veren
    -1.42
    がなく
    -1.41
    quartier
    -1.36
    manız
    -1.36
    ledad
    -1.34
     reizen
    -1.34
    geladen
    -1.34
     göm
    -1.34
    POSITIVE LOGITS
     time
    1.64
     each
    1.44
    ’
    1.43
     beziehungs
    1.34
    <th>
    1.32
     well
    1.30
    er
    1.28
    L
    1.26
     quickly
    1.25
    It
    1.24
    Activations Density 0.001%

    No Known Activations