© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54106
    Prev
    Next
    INDEX
    Explanations

    following punctuation

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

    The neuron strongly fires on end‐of‐sentence punctuation marks (especially the period “.” token).

    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
    OwnProperty
    -1.20
     систему
    -1.16
    かります
    -0.98
    titudine
    -0.97
    莳
    -0.94
    λλά
    -0.94
     malle
    -0.93
     своей
    -0.93
     have
    -0.91
    OWER
    -0.91
    POSITIVE LOGITS
     trône
    1.12
    ロシア
    1.07
     papild
    0.87
     RECOMMEND
    0.85
     zatem
    0.84
     as
    0.84
    harris
    0.84
     along
    0.83
     These
    0.82
    ilaku
    0.82
    Activations Density 0.157%

    No Known Activations