© 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. 34-GEMMASCOPE-RES-131K
    4. 115474
    Prev
    Next
    INDEX
    Explanations

    assignment and equality checks

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

    This neuron detects numeric index or coordinate expressions inside parentheses (e.g. “a(5,1)”–style tuples).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ++$
    -0.89
    -%
    -0.88
     hadn
    -0.87
    spesies
    -0.80
     wykorzyst
    -0.79
    leştir
    -0.79
     havia
    -0.78
    耐心
    -0.77
    -${
    -0.75
     düşünü
    -0.74
    POSITIVE LOGITS
     =
    2.92
    }}=
    2.52
    )=
    2.28
     }}=
    2.27
    }=
    2.13
    )}=
    2.02
    ]=
    1.91
    })=
    1.89
     $=
    1.77
    =
    1.72
    Activations Density 0.209%

    No Known Activations