© 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. 93101
    Prev
    Next
    INDEX
    Explanations

    final / last / ordinal numbers

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

    The neuron strongly activates on tokens made up of long repeated characters—e.g. sequences of dashes or strings of digits—regardless of context.

    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
     nung
    -0.87
    nung
    -0.87
    oros
    -0.85
    ㎏
    -0.84
    чками
    -0.84
     πρώ
    -0.84
     this
    -0.84
    first
    -0.83
    \"");
    -0.83
    lection
    -0.82
    POSITIVE LOGITS
    最後に
    1.02
     lastly
    0.99
    Finally
    0.98
     Lastly
    0.98
    Lastly
    0.96
     autre
    0.95
     enfin
    0.93
     final
    0.93
     miscellaneous
    0.92
     наконец
    0.88
    Activations Density 0.050%

    No Known Activations