© 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. 98676
    Prev
    Next
    INDEX
    Explanations

    awareness days and months

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

    The neuron flags calendar‐style event names and observance periods (e.g. “X Month,” “Y Day,” etc.).

    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
     homicidio
    -1.12
     only
    -1.09
     that
    -1.02
     (;;
    -1.02
     from
    -1.02
    }\
    -1.01
    sk
    -1.00
    eth
    -0.99
     offensichtlich
    -0.99
    会议
    -0.99
    POSITIVE LOGITS
    Kolor
    1.17
    Merken
    1.15
    wór
    1.13
     keten
    1.12
    Ayrıca
    1.11
    Lähde
    1.07
    Bericht
    1.05
    Versch
    1.05
     rette
    1.05
     beker
    1.04
    Activations Density 0.033%

    No Known Activations