© 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. 47683
    Prev
    Next
    INDEX
    Explanations

    about or exploring themes

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

    The neuron fires on thematic or topic-marker words and phrases that introduce or frame a subject (e.g. “deals,” “addressing,” “themes,” “family,” “memory,” “trauma,” “importance,” 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
     главе
    -0.88
    ̉
    -0.85
    membered
    -0.81
    几十
    -0.80
     могат
    -0.80
    ję
    -0.79
    satunya
    -0.79
    禀
    -0.79
     watering
    -0.78
    髦
    -0.78
    POSITIVE LOGITS
     family
    1.50
     friendship
    1.48
     loss
    1.48
     identity
    1.27
     loyalty
    1.23
     how
    1.22
     relationships
    1.21
     what
    1.20
     gäng
    1.18
     FRIEND
    1.13
    Activations Density 0.043%

    No Known Activations