© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25693
    Prev
    Next
    INDEX
    Explanations

    code snippets and file paths

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

    The neuron fires on programming identifiers and technical names (e.g. variable/property names, module or parameter names).

    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
     zerstört
    -0.95
     and
    -0.93
     Biodiversity
    -0.90
    prised
    -0.84
     sostitu
    -0.84
    の森
    -0.83
    émoc
    -0.83
    исленность
    -0.82
    ⊻
    -0.81
     different
    -0.79
    POSITIVE LOGITS
     jellemző
    0.96
    의
    0.91
     derde
    0.83
    过头
    0.81
    XR
    0.80
    Rust
    0.79
     része
    0.79
    Ру
    0.78
    Ach
    0.77
    yep
    0.77
    Activations Density 0.056%

    No Known Activations