© 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. 10-GEMMASCOPE-RES-131K
    7. 42433
    Prev
    Next
    INDEX
    Explanations

    look at

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

    The neuron fires on instances of the phrase “look at,” typically when pointing the reader to an external reference or resource.

    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
     That
    -2.66
    That
    -2.42
     You
    -2.28
     It
    -2.20
    It
    -2.14
    If
    -2.11
     With
    -2.11
     überras
    -2.02
    You
    -1.88
     But
    -1.87
    POSITIVE LOGITS
    odyear
    2.14
    镦
    2.13
     Alemanha
    2.13
     enorme
    2.09
    PostInfinity
    2.06
    
    1.96
    dienne
    1.96
    quées
    1.92
    𞤮
    1.91
    НЫХ
    1.89
    Activations Density 0.009%

    No Known Activations