© 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. 10-GEMMASCOPE-RES-131K
    7. 1454
    Prev
    Next
    INDEX
    Explanations

    condemn and condemnation

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

    The neuron activates on occurrences of “condemn” (and its morphological variants).

    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
    峮
    -2.95
    栳
    -2.91
    텃
    -2.75
    *}$
    -2.73
    荜
    -2.73
    樒
    -2.70
    𖣘
    -2.70
    蕻
    -2.63
    𖤍
    -2.63
    頂き
    -2.61
    POSITIVE LOGITS
    ↵
    5.28
    1
    3.11
    鸶
    3.05
    0
    2.75
    ’
    2.64
    鸯
    2.53
    E
    2.45
    无力
    2.44
    莫名
    2.44
    T
    2.41
    Activations Density 0.002%

    No Known Activations