© 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. 11318
    Prev
    Next
    INDEX
    Explanations

    mapping functions and class names

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

    return statements in programming code, particularly when returning objects, variables, or function calls.

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

    The neuron is looking for object‐ or pointer‐member access expressions (the use of “.” or “->” to call a method or access a field).

    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
    Răspunde
    -1.36
     autre
    -1.29
    бря
    -1.28
     mètres
    -1.28
     include
    -1.25
     téléchargement
    -1.22
    Its
    -1.19
    歲
    -1.18
     evtl
    -1.18
     Tropfen
    -1.16
    POSITIVE LOGITS
     most
    1.70
     usable
    1.36
     when
    1.32
     since
    1.31
     more
    1.30
     similar
    1.30
     for
    1.29
     because
    1.28
     cuando
    1.27
     cheaper
    1.27
    Activations Density 0.049%

    No Known Activations