© 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. 26502
    Prev
    Next
    INDEX
    Explanations

    steps and updates

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

    The neuron activates on schema‐ or metadata‐style identifiers (column/field names or XML tags).

    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
     chré
    -1.19
     for
    -1.14
     τὰ
    -1.09
     τὴν
    -1.03
     religieuses
    -1.01
     canadensis
    -1.00
    ₇
    -0.97
     αὐ
    -0.96
     dbName
    -0.94
     anunció
    -0.94
    POSITIVE LOGITS
     completed
    1.48
     later
    1.41
     pozdě
    1.33
     subsequent
    1.32
     done
    1.31
     outcome
    1.28
    ּוֹ
    1.22
    ֵּ
    1.17
     finished
    1.16
     date
    1.16
    Activations Density 0.010%

    No Known Activations