© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8533
    Prev
    Next
    INDEX
    Explanations

    context objects

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

    The neuron activates on occurrences of the identifier “ctx” (the common abbreviation for a programming context object).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     each
    -2.59
     of
    -2.53
    ibouti
    -2.33
     każdego
    -2.31
    Ꭳ
    -2.27
    蹂
    -2.20
    0
    -2.19
    नलोड
    -2.17
    褫
    -2.17
    ,”
    -2.16
    POSITIVE LOGITS
    镡
    2.22
                    
    2.22
    硨
    2.20
    镦
    2.17
    geſ
    2.17
    ?"
    2.14
     explica
    2.05
    駡
    2.02
    賔
    2.00
    transQ
    1.98
    Activations Density 0.000%

    No Known Activations