© 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. 32489
    Prev
    Next
    INDEX
    Explanations

    rating scale

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

    This neuron strongly activates on tokens that mark truncated or expandable UI elements—e.g. ellipses, “view more,” and similar prompts indicating hidden continuation.

    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
     sostenible
    -0.90
     کابل
    -0.86
    enjoy
    -0.86
    rectangle
    -0.83
    alakip
    -0.79
    ssant
    -0.79
    rouse
    -0.79
     Retriever
    -0.77
    tite
    -0.76
    encode
    -0.76
    POSITIVE LOGITS
     schreck
    0.84
     other
    0.81
     Kerja
    0.78
    culadora
    0.77
     millon
    0.75
     отзыв
    0.74
     excellent
    0.74
     very
    0.74
    iverr
    0.73
     highly
    0.73
    Activations Density 0.009%

    No Known Activations