© 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. 34-GEMMASCOPE-RES-131K
    4. 48347
    Prev
    Next
    INDEX
    Explanations

    scientific and technical content

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

    hexadecimal identifiers in code like GUIDs and project IDs.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on hexadecimal identifier tokens (e.g. the hex-digit groups in GUID/UUID 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_34/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
    enservice
    -0.86
     respekt
    -0.83
     kompakt
    -0.82
    襖
    -0.80
    JOSEPH
    -0.79
    摆手
    -0.78
     géographie
    -0.77
     canst
    -0.77
     masker
    -0.77
     anyone
    -0.77
    POSITIVE LOGITS
    Assembly
    0.93
     assembly
    0.90
     Assembly
    0.88
    tonsoft
    0.79
     naughty
    0.77
     PA
    0.76
    vit
    0.73
     nuisance
    0.72
    bat
    0.71
    ウィ
    0.71
    Activations Density 0.002%

    No Known Activations