© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64801
    Prev
    Next
    INDEX
    Explanations

    data conversion, carrier, then https

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

    The neuron responds to unusually long individual tokens (i.e. words or identifiers of many 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
    anteil
    -0.88
    游戏介绍
    -0.87
    various
    -0.87
     Même
    -0.85
     other
    -0.85
    lässt
    -0.84
    各種
    -0.83
     diversos
    -0.82
    各类
    -0.82
    ÑOS
    -0.81
    POSITIVE LOGITS
     during
    1.04
     when
    0.98
     by
    0.96
    convertView
    0.88
     which
    0.88
     with
    0.84
    BufferedImage
    0.83
    "}}
    0.83
     at
    0.82
    stringBuffer
    0.82
    Activations Density 0.101%

    No Known Activations