© 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. 103493
    Prev
    Next
    INDEX
    Explanations

    explaining to

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

    The neuron fires on occurrences of the phrase “explain to …,” i.e. requests asking someone to explain something.

    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
    </b>
    -2.13
    s
    -1.75
    ．．
    -1.74
    '
    -1.55
     héroe
    -1.53
     archived
    -1.49
     grito
    -1.47
     retrato
    -1.46
    ↵
    -1.46
    遽
    -1.45
    POSITIVE LOGITS
    </h3>
    2.44
     same
    2.14
    ,’
    1.76
     ';
    1.73
     godziny
    1.66
     όταν
    1.65
     potrafi
    1.62
    al
    1.61
    us
    1.59
    el
    1.58
    Activations Density 0.027%

    No Known Activations