© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67422
    Prev
    Next
    INDEX
    Explanations

    currently holding positions

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

    The neuron activates on formal professional or organizational titles (e.g. President, Director, Professor).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     later
    -1.70
     during
    -1.64
     then
    -1.64
     eventually
    -1.52
     damals
    -1.50
     would
    -1.49
    もあった
    -1.33
     before
    -1.32
     early
    -1.30
     were
    -1.29
    POSITIVE LOGITS
     currently
    1.91
    currently
    1.60
     сейчас
    1.53
    当前
    1.38
     now
    1.33
    Currently
    1.27
     현재
    1.26
     momente
    1.24
    目前
    1.22
     Currently
    1.22
    Activations Density 0.046%

    No Known Activations