© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28464
    Prev
    Next
    INDEX
    Explanations

    alternatives or contrasting conditions

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

    This neuron specifically detects the adverb “otherwise.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    蟊
    -2.19
    derdag
    -2.17
    遊ぶ
    -2.13
    艽
    -2.09
    宝物
    -2.06
    飏
    -2.05
    </b>
    -2.03
     nowadays
    -2.02
    section
    -2.02
    靫
    -1.95
    POSITIVE LOGITS
    The
    3.63
    </h3>
    2.56
    。
    2.53
    what
    2.41
    та
    2.38
    是
    2.25
                
    2.22
    om
    2.22
    <strong>
    2.16
    ａ
    2.14
    Activations Density 0.006%

    No Known Activations