© 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. 34-GEMMASCOPE-RES-131K
    7. 37708
    Prev
    Next
    INDEX
    Explanations

    redemption and redeem

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

    The neuron detects occurrences of “redeem”/“redemption” (and related forms like “redeemed” or “forgive us”) in text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     enfer
    -0.78
     scraped
    -0.77
    xito
    -0.75
    稹
    -0.75
    折叠
    -0.75
    ⏭
    -0.73
    パク
    -0.72
    يميديا
    -0.72
    ATELL
    -0.72
    呜
    -0.71
    POSITIVE LOGITS
     redemption
    3.61
     redeem
    3.19
     Redemption
    2.92
    Rede
    2.89
    rede
    2.77
     redeemed
    2.72
     redeeming
    2.69
     rede
    2.47
     Rede
    2.34
     Redeemer
    2.11
    Activations Density 0.020%

    No Known Activations