© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 58799
    Prev
    Next
    INDEX
    Explanations

    end of code blocks

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

    The neuron fires strongly on numeric literal tokens (i.e. sequences of digits).

    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
    }$}
    -1.00
     vaikka
    -0.93
    ándote
    -0.91
     cũng
    -0.90
    elif
    -0.88
     wakati
    -0.88
     tirantes
    -0.86
     también
    -0.86
    っちゃう
    -0.85
    pita
    -0.85
    POSITIVE LOGITS
     finally
    4.84
    finally
    4.41
    Finally
    3.86
     Finally
    3.67
     наконец
    3.58
     finalmente
    3.41
     enfin
    2.83
     FINALLY
    2.69
     akhirnya
    2.66
     schließlich
    2.59
    Activations Density 0.001%

    No Known Activations