© 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. 73093
    Prev
    Next
    INDEX
    Explanations

    LINQ, C#, Python, Java

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

    The neuron fires on identifiers in code import/include directives (e.g. header or library names after “#include”, “import”, or “using”).

    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
     it
    -1.23
    Fonto
    -1.19
     Obviously
    -1.09
     Before
    -1.04
     one
    -1.02
     From
    -1.02
     Not
    -1.01
    笑笑
    -0.98
     Using
    -0.98
     With
    -0.97
    POSITIVE LOGITS
    щено
    1.12
    caba
    1.05
     eſ
    1.04
     IRELAND
    1.02
     interfaz
    1.02
     :/
    1.01
    😦
    0.96
     encore
    0.96
    ΄
    0.95
     '*'
    0.95
    Activations Density 0.010%

    No Known Activations