© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38274
    Prev
    Next
    INDEX
    Explanations

    defining map and generic types

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

    This neuron detects generic type declarations in code, i.e. the angle-bracket syntax (e.g. “<…>”) used for templated or parameterized types.

    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
    ～！
    -1.07
    ただし
    -1.05
    voted
    -1.02
    などの
    -1.00
     několik
    -0.98
    ⎧
    -0.98
    もありますが
    -0.94
    жом
    -0.94
     HAPPENED
    -0.91
    …？
    -0.91
    POSITIVE LOGITS
     each
    1.45
    <tr>
    1.11
    每
    1.02
     every
    1.02
     chacune
    1.00
    </b>
    0.99
     chaque
    0.98
     deporte
    0.97
    較
    0.95
     antigo
    0.94
    Activations Density 0.011%

    No Known Activations