© 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. 34-GEMMASCOPE-RES-131K
    7. 30102
    Prev
    Next
    INDEX
    Explanations

    tier classification levels

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

    The neuron detects occurrences of the word “tier” (often paired with a number) indicating categorical or hierarchical levels.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    uyan
    -0.85
    cadilly
    -0.85
     Rocco
    -0.82
     fordert
    -0.81
    ærk
    -0.77
     schutz
    -0.76
    sikker
    -0.76
     Broth
    -0.76
     antwortete
    -0.75
    ěla
    -0.73
    POSITIVE LOGITS
     Tier
    1.41
    Tier
    1.32
     tier
    1.31
    tier
    1.18
    TIER
    1.01
     tiered
    0.98
    NEY
    0.93
     المكان
    0.87
     kompon
    0.87
     tulis
    0.86
    Activations Density 0.013%

    No Known Activations