© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103668
    Prev
    Next
    INDEX
    Explanations

    id followed by node or class

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

    This neuron detects occurrences of “Id” or “id” tokens used as code identifiers (often alongside numeric field or attribute 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_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
     actually
    -1.13
    there
    -1.09
    2
    -1.09
     basically
    -1.07
     possibly
    -1.06
    R
    -1.04
     remarkable
    -1.03
    4
    -1.03
    It
    -1.02
    </td>
    -1.02
    POSITIVE LOGITS
    pId
    1.10
    код
    1.07
    ="@+
    1.06
    ÉE
    1.03
    pflanzen
    1.02
     ſon
    1.02
    entic
    1.01
    ässä
    1.01
     kent
    1.01
     ise
    1.01
    Activations Density 0.088%

    No Known Activations