© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78219
    Prev
    Next
    INDEX
    Explanations

    what constitutes groups

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

    The neuron simply lights up on very high‐frequency/common words (e.g. “people,” “they,” “are,” “students,” 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_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
    汆
    -1.02
    عه
    -0.93
     основан
    -0.93
    χω
    -0.86
    '];
    -0.84
    อล
    -0.84
    کا
    -0.84
     hvil
    -0.84
    nullable
    -0.84
    minal
    -0.82
    POSITIVE LOGITS
     constitute
    2.14
     constitutes
    1.75
     comprises
    1.51
    构成
    1.51
     represent
    1.50
     comprise
    1.49
     represents
    1.45
     constituting
    1.36
     составля
    1.34
    组成
    1.33
    Activations Density 0.061%

    No Known Activations