© 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. 71584
    Prev
    Next
    INDEX
    Explanations

    hexadecimal identifiers and code snippets

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

    The neuron fires strongly on long alphanumeric identifier tokens—especially hexadecimal or numeric ID strings.

    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
     and
    -1.55
     on
    -1.41
    lampe
    -1.30
     or
    -1.30
    %"),
    -1.22
    dekat
    -1.22
     in
    -1.16
    prnewswire
    -1.13
    FFEE
    -1.13
     what
    -1.12
    POSITIVE LOGITS
    が
    1.22
     Ayur
    1.20
    5
    1.20
     стихотво
    1.17
    .¹
    1.15
     Irrit
    1.14
     exasper
    1.14
     erec
    1.14
     Magen
    1.14
     robus
    1.13
    Activations Density 0.005%

    No Known Activations