© 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. 98788
    Prev
    Next
    INDEX
    Explanations

    Rights Reserved

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

    The neuron activates on individual “named” content tokens—e.g. people’s names, code‐identifiers, or other standalone entity words.

    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
    ：　
    -0.98
    　(
    -0.94
     divertida
    -0.91
     klat
    -0.89
    ofed
    -0.85
    ⁞
    -0.84
    ченных
    -0.83
     før
    -0.83
     ennen
    -0.83
    isons
    -0.82
    POSITIVE LOGITS
     注文
    0.92
    though
    0.89
    jenige
    0.88
    یزات
    0.87
    assuming
    0.85
    Might
    0.84
     発送
    0.84
    Espec
    0.83
    がありますが
    0.81
     order
    0.79
    Activations Density 0.001%

    No Known Activations