© 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. 95749
    Prev
    Next
    INDEX
    Explanations

    and positive qualities

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

    The neuron fires on mid‐frequency, formal content words (especially abstract nouns and verbs) typical of expository or instructional passages.

    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
     اطلع
    -1.23
    Beautifully
    -1.19
     akses
    -1.14
    bilirsiniz
    -1.13
     materiale
    -1.13
     ją
    -1.09
     pude
    -1.09
     deklar
    -1.08
     induk
    -1.08
    kkue
    -1.07
    POSITIVE LOGITS
     "
    1.13
     [
    1.07
     a
    1.05
    J
    1.02
    ↵↵
    1.01
     as
    1.00
    "
    0.97
    n
    0.96
    شته
    0.96
     results
    0.96
    Activations Density 0.030%

    No Known Activations