© 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. 34-GEMMASCOPE-RES-131K
    7. 64986
    Prev
    Next
    INDEX
    Explanations

    related to containing or accompanying

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

    The neuron fires on occurrences of the verb “contain” (in bare, ‑ing, or ‑ed form) or closely related tokens (e.g. “containing,” “contained,” “accompanying”) in boilerplate/legal/metadata text.

    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
     sosial
    -0.79
     first
    -0.75
     new
    -0.75
    Lame
    -0.75
     supremely
    -0.74
     anys
    -0.73
    尊重
    -0.72
    runOnUiThread
    -0.71
     unhas
    -0.70
     continual
    -0.69
    POSITIVE LOGITS
     a
    1.00
    ()).
    0.91
    WriteBarrier
    0.89
    gridx
    0.86
    ningar
    0.85
    enic
    0.85
    seud
    0.83
    懶
    0.82
    วย
    0.82
    rfloor
    0.81
    Activations Density 0.004%

    No Known Activations