© 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. 10-GEMMASCOPE-RES-131K
    7. 12990
    Prev
    Next
    INDEX
    Explanations

    as a role or identity

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

    The neuron is specifically detecting occurrences of the word “as.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     following
    -1.71
     they
    -1.65
     relacionadas
    -1.48
     reservados
    -1.43
     that
    -1.42
     preparados
    -1.35
    ために
    -1.34
     after
    -1.33
    のための
    -1.33
     atentos
    -1.32
    POSITIVE LOGITS
     a
    1.94
     bahkan
    1.91
    Beantwoorden
    1.64
     حتی
    1.61
    甚至
    1.55
    heureux
    1.54
    ان
    1.50
    weiterlesen
    1.49
     összefoglal
    1.49
     Shouldn
    1.46
    Activations Density 0.024%

    No Known Activations