© 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. 34-GEMMASCOPE-RES-131K
    7. 90770
    Prev
    Next
    INDEX
    Explanations

    programming code structures

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

    The neuron fires on identifiers that name user-defined types or classes (e.g. type or class names in code).

    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
     The
    -1.22
     the
    -1.17
     their
    -1.08
     its
    -1.05
    ‘
    -0.98
     M
    -0.97
        
    -0.96
    laboration
    -0.93
     a
    -0.91
     Finally
    -0.91
    POSITIVE LOGITS
     seksi
    1.25
     exemplos
    1.24
     interfaz
    1.23
     egent
    1.18
    gliche
    1.13
    '/>
    1.12
    /}.
    1.12
    èges
    1.10
     maksi
    1.09
    '>
    1.09
    Activations Density 0.027%

    No Known Activations