© 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. 34-GEMMASCOPE-RES-131K
    7. 91042
    Prev
    Next
    INDEX
    Explanations

    names and dates

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

    The neuron fires on unusually rare or complex tokens (e.g. obscure words, numbers, or other low‐frequency items).

    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
     Luzern
    -0.89
    用户
    -0.88
     Finney
    -0.85
    \}\\
    -0.82
    ]]>
    -0.80
    bereit
    -0.78
    Véxase
    -0.78
    GUILayout
    -0.77
    :「
    -0.76
    uent
    -0.76
    POSITIVE LOGITS
    lol
    0.88
    hehe
    0.87
     inspired
    0.87
     getVersion
    0.83
     umgekehrt
    0.81
     вижу
    0.81
    inspired
    0.81
     lieben
    0.80
    глежда
    0.80
     effectivement
    0.79
    Activations Density 0.001%

    No Known Activations