© 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. 60725
    Prev
    Next
    INDEX
    Explanations

    underlying mechanisms

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

    The neuron flags technical language describing underlying biological or molecular mechanisms (e.g. “underlying,” “mechanisms,” “molecular,” 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
    Derivative
    -0.87
     memen
    -0.85
     dagen
    -0.82
     correcto
    -0.82
     paquet
    -0.81
    ROUTINE
    -0.80
    🥚
    -0.79
     layak
    -0.78
     geboren
    -0.78
     cocción
    -0.78
    POSITIVE LOGITS
     mechanisms
    2.63
     mechanism
    2.52
     underlying
    2.36
     molecular
    1.91
    mechan
    1.76
    MECHAN
    1.75
    mechanism
    1.73
     механи
    1.72
    underlying
    1.69
    Mechanism
    1.68
    Activations Density 0.546%

    No Known Activations