© 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. 22-GEMMASCOPE-RES-131K
    4. 28544
    Prev
    Next
    INDEX
    Explanations

    nested for loops

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

    The neuron strongly fires on loop‐header tokens—especially the “for (” syntax and the loop variable/type declarations—i.e. it identifies for‐loops.

    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
    Alamat
    -1.30
     ſi
    -1.28
     APPELL
    -1.27
    
    -1.24
     parachoque
    -1.23
     rése
    -1.22
     calendriers
    -1.19
     favoris
    -1.16
     klim
    -1.16
     transparentes
    -1.15
    POSITIVE LOGITS
     No
    1.30
     L
    1.28
     Due
    1.25
    w
    1.23
    b
    1.21
     In
    1.20
    …
    1.20
     also
    1.17
     S
    1.16
     N
    1.16
    Activations Density 0.002%

    No Known Activations