© 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. 93286
    Prev
    Next
    INDEX
    Explanations

    x3x

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

    This neuron activates on hexadecimal numbers or hex literals (sequences of 0–9 and A–F characters).

    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
    tifie
    -1.24
    ことも
    -1.16
    んですが
    -1.13
     zijne
    -1.13
    ようですが
    -1.12
    帰って
    -1.08
    を行います
    -1.07
    づけ
    -1.05
    に行って
    -1.04
    nito
    -1.03
    POSITIVE LOGITS
     other
    1.31
     another
    1.22
     numerous
    1.13
     probably
    1.09
     mostly
    1.05
     more
    1.04
     possibly
    1.03
    食器
    1.02
     sometimes
    1.01
    そのため
    1.00
    Activations Density 0.027%

    No Known Activations