© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84279
    Prev
    Next
    INDEX
    Explanations

    database backup, PGP word, bone cement, athletic training

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

    The neuron fires strongly on the single key noun or term that names the document’s main subject (its title/topic word).

    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
     стаття
    -1.43
     biela
    -1.31
    Così
    -1.28
     triko
    -1.27
    pompa
    -1.27
     малко
    -1.24
    Molto
    -1.22
     pleaſure
    -1.22
    uniqlo
    -1.21
    borsa
    -1.20
    POSITIVE LOGITS
    a
    1.32
    e
    1.21
    y
    1.21
    l
    1.21
    d
    1.21
    o
    1.20
    f
    1.19
    ar
    1.14
    p
    1.14
    ;
    1.13
    Activations Density 0.130%

    No Known Activations