© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35111
    Prev
    Next
    INDEX
    Explanations

    as i said

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

    The neuron strongly activates on the discourse marker “again,” i.e. instances of the word “again” used to reintroduce or emphasize a point.

    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
     again
    -1.17
    鏇
    -1.06
     atriz
    -1.03
    casts
    -1.00
     after
    -0.96
    katapos
    -0.95
    cómo
    -0.94
    𓄹
    -0.94
    después
    -0.94
     senaste
    -0.94
    POSITIVE LOGITS
     soltanto
    0.96
     \
    0.92
     רק
    0.90
    RTCK
    0.90
    werte
    0.89
     tylko
    0.88
    一定要
    0.88
     surpresa
    0.88
     فقط
    0.87
     jestem
    0.87
    Activations Density 0.007%

    No Known Activations