© 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. 89962
    Prev
    Next
    INDEX
    Explanations

    end of code blocks and data

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

    The neuron fires on numeric literals (numbers) in code or text.

    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
     vérit
    -0.84
     Riproduzione
    -0.81
    темати
    -0.81
    ಿನ
    -0.80
     butik
    -0.80
    manan
    -0.79
    แทน
    -0.78
    GetChild
    -0.78
    (',');
    -0.76
     سیل
    -0.75
    POSITIVE LOGITS
     end
    1.20
     END
    1.17
    END
    1.08
     NULL
    1.07
    end
    1.06
     끝
    1.03
     terminate
    1.03
     End
    1.02
    NULL
    0.98
    End
    0.94
    Activations Density 0.004%

    No Known Activations