© 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. 21782
    Prev
    Next
    INDEX
    Explanations

    importance, need, value, significance

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

    This neuron detects abstract evaluative nouns expressing significance or necessity (e.g. “importance,” “value,” “need”).

    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
     the
    -1.42
     menghubungi
    -1.34
     wurden
    -1.33
     они
    -1.29
    ⼈
    -1.28
     you
    -1.27
     I
    -1.27
     They
    -1.26
    arashtra
    -1.23
     sprawd
    -1.20
    POSITIVE LOGITS
     and
    1.59
     of
    1.36
    andReturn
    1.30
     campeão
    1.27
    :\/\/
    1.27
    垍
    1.27
     Ruß
    1.23
     महत्व
    1.23
    mann
    1.20
    {\$
    1.18
    Activations Density 0.036%

    No Known Activations