© 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. 10-GEMMASCOPE-RES-131K
    7. 7735
    Prev
    Next
    INDEX
    Explanations

    third-party services and resources

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

    The neuron specializes in detecting references to “third-party” (including “3rd party”) mentions.

    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
     Then
    -2.17
     The
    -1.96
    }$
    -1.92
     turns
    -1.91
      
    -1.87
    1
    -1.86
     are
    -1.82
    .
    -1.81
    вит
    -1.76
     tendrá
    -1.74
    POSITIVE LOGITS
    勠
    2.86
    ஂ
    2.41
    ेमाल
    2.28
    e
    2.23
    瑧
    2.22
    梣
    2.20
    沇
    2.17
     शुर
    2.13
     berpikir
    2.11
    垕
    2.09
    Activations Density 0.004%

    No Known Activations