© 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. 54204
    Prev
    Next
    INDEX
    Explanations

    hexadecimal identifiers and codes

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

    The neuron is looking for long sequences of hexadecimal characters (e.g. GUIDs, hashes, or hex addresses).

    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
    -2.75
     or
    -1.88
     should
    -1.85
     as
    -1.82
     an
    -1.74
     on
    -1.72
     will
    -1.68
     so
    -1.61
     no
    -1.58
     like
    -1.50
    POSITIVE LOGITS
    などが
    1.84
    <bos>
    1.73
    それでは
    1.59
     APPE
    1.59
    個人的には
    1.57
     avowed
    1.57
    もあって
    1.57
     CERTAIN
    1.56
    ちなみに
    1.55
    Belgique
    1.54
    Activations Density 0.020%

    No Known Activations