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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71755
    Prev
    Next
    INDEX
    Explanations

    end of file or script

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

    The neuron fires on tokens commonly found in error‐ or exception‐style messages (e.g. “EOF,” “end,” “file,” “overflow,” “error,” etc.).

    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
     ledig
    -1.13
    ﻷ
    -1.04
    вам
    -1.02
     száz
    -1.01
     csoport
    -1.00
     ägg
    -0.99
     ideen
    -0.93
    aluno
    -0.93
    fritt
    -0.93
    ällning
    -0.92
    POSITIVE LOGITS
    vaila
    0.98
     end
    0.97
    finity
    0.94
    pressure
    0.91
     терпе
    0.85
    aturi
    0.84
     Examin
    0.83
     continuation
    0.82
     Continuation
    0.82
     Prova
    0.82
    Activations Density 0.005%

    No Known Activations