© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9166
    Prev
    Next
    INDEX
    Explanations

    questions and answers

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

    This neuron fires on code/document snippets naming API or JSON data fields (e.g. consumer_key, access_token, screen_name, tweet_limit)—in particular Twitter-related field identifiers.

    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
     you
    -1.56
     should
    -1.55
    <h2>
    -1.51
    ❗
    -1.49
    .\\
    -1.48
    Because
    -1.48
     ؛
    -1.48
     благодаря
    -1.47
     because
    -1.43
    When
    -1.41
    POSITIVE LOGITS
     continúas
    1.45
    が付いて
    1.45
     pouze
    1.42
    ܆
    1.42
     parfois
    1.38
    を失
    1.35
    stateMutability
    1.34
     funcionan
    1.31
     FORCES
    1.31
     gevallen
    1.30
    Activations Density 0.008%

    No Known Activations