© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44146
    Prev
    Next
    INDEX
    Explanations

    making an effort

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

    The neuron fires on adverbial or adjectival intensifiers that strengthen or urge actions (e.g. “hard” in “work hard,” “plenty” in “drink plenty,” “hurry” in “hurry up”).

    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
     into
    -1.59
    一起去
    -1.37
     dönd
    -1.34
     diversos
    -1.32
     swift
    -1.30
     vieron
    -1.30
     determinado
    -1.30
     Som
    -1.29
     longtime
    -1.28
     Cons
    -1.27
    POSITIVE LOGITS
    кроссовки
    1.65
    踽
    1.47
     territoriale
    1.45
     tred
    1.39
     纹身
    1.38
     farmacia
    1.37
     samar
    1.35
     رابطه
    1.30
     插图
    1.29
     kazak
    1.28
    Activations Density 0.009%

    No Known Activations