© 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. 10-GEMMASCOPE-RES-131K
    4. 102162
    Prev
    Next
    INDEX
    Explanations

    null, none, true, 0

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

    The neuron flags literal constant values (e.g. Boolean, null/None, or YES/NO tokens) in code or configuration.

    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
     "
    -1.53
     '
    -1.42
    ってください
    -1.36
     chaleco
    -1.35
     all
    -1.34
    ="
    -1.34
    providedIn
    -1.30
     ..."
    -1.29
     gorro
    -1.29
     always
    -1.28
    POSITIVE LOGITS
    olition
    1.45
    savevideo
    1.45
     هناك
    1.42
     Pristup
    1.38
    kezik
    1.33
    Fotó
    1.32
     photolibrary
    1.29
    ָּ
    1.27
    ּוֹ
    1.27
     HAPPY
    1.27
    Activations Density 0.061%

    No Known Activations