© 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. 39572
    Prev
    Next
    INDEX
    Explanations

    hex codes and numbers

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

    The neuron detects contiguous hexadecimal digit sequences (as used in CSS color codes and similar hex representations).

    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
    Ď
    -1.62
    贋
    -1.49
     веке
    -1.34
    xvii
    -1.30
    ctober
    -1.29
     Czę
    -1.24
     Głów
    -1.23
    jours
    -1.17
     personalizadas
    -1.16
    вик
    -1.16
    POSITIVE LOGITS
    er
    1.26
    P
    1.22
    r
    1.20
    u
    1.20
    d
    1.18
    g
    1.17
    f
    1.17
    这也是
    1.16
    N
    1.16
    te
    1.15
    Activations Density 0.001%

    No Known Activations