© 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. 34-GEMMASCOPE-RES-131K
    7. 2623
    Prev
    Next
    INDEX
    Explanations

    persists or remains

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

    The neuron lights up on semantically “heavy” words—especially key nouns and other content-bearing terms—marking the main topical or descriptive vocabulary in a passage.

    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
     icing
    -0.83
     表
    -0.78
     zonder
    -0.74
    Tudo
    -0.74
     ранее
    -0.73
     Feedback
    -0.72
     jaw
    -0.72
     DX
    -0.71
    Yi
    -0.71
     outcome
    -0.71
    POSITIVE LOGITS
     alive
    1.55
     memory
    1.26
     memories
    1.23
     remembered
    1.22
     remain
    1.20
     continue
    1.12
     survives
    1.11
     زنده
    1.09
     lives
    1.08
     live
    1.07
    Activations Density 0.013%

    No Known Activations