© 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. 53944
    Prev
    Next
    INDEX
    Explanations

    Did you questions

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

    The neuron selectively detects occurrences of the word “did” (in any casing) in the text.

    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
    There
    -1.34
     if
    -1.20
    логии
    -1.20
    there
    -1.16
    them
    -1.16
     there
    -1.12
    CONCLUSIONS
    -1.09
    ENCIL
    -1.07
     если
    -1.05
     там
    -1.05
    POSITIVE LOGITS
     they
    2.48
     you
    1.92
     it
    1.64
     anyone
    1.54
     we
    1.47
     môžu
    1.35
    actic
    1.20
    ’
    1.19
     she
    1.19
     môžete
    1.15
    Activations Density 0.006%

    No Known Activations