© 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. 10-GEMMASCOPE-RES-131K
    7. 21724
    Prev
    Next
    INDEX
    Explanations

    deprecated features

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

    The neuron activates on occurrences of the term “deprecated,” i.e. it spots deprecation notices.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    躥
    -2.98
    ſſen
    -2.63
    儅
    -2.59
    跸
    -2.56
     inteligen
    -2.45
    Spolja
    -2.39
    趿
    -2.38
     bytu
    -2.36
    嘥
    -2.36
    bluza
    -2.34
    POSITIVE LOGITS
    ↵
    3.53
    ve
    3.00
    me
    2.47
    D
    2.47
    </em>
    2.47
    ne
    2.45
    ("
    2.42
    かつて
    2.41
    K
    2.38
    <em>
    2.34
    Activations Density 0.007%

    No Known Activations