© 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. 22-GEMMASCOPE-RES-131K
    7. 95480
    Prev
    Next
    INDEX
    Explanations

    creation and action verbs

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

    The neuron responds most strongly to unusually long tokens—i.e. it flags words with a large character length.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ...
    -1.58
    de
    -1.55
    [
    -1.49
    ?
    -1.45
    ar
    -1.44
    —
    -1.44
    an
    -1.42
    を
    -1.41
    un
    -1.38
     "
    -1.37
    POSITIVE LOGITS
    総評
    1.54
    ＊＊＊＊
    1.53
    敺
    1.50
    にほんブログ村
    1.47
    comida
    1.41
    んだよね
    1.38
    もうすぐ
    1.36
     decidido
    1.36
    camisetas
    1.35
    久し
    1.34
    Activations Density 0.165%

    No Known Activations