© 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. 10-GEMMASCOPE-RES-131K
    4. 59855
    Prev
    Next
    INDEX
    Explanations

    . followed by pronouns or new clauses

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

    The neuron flags imperative calls to action—phrases inviting the reader to do something (e.g. “check out,” “take a look,” “go and…”).

    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
    </h5>
    -1.35
    玊
    -1.34
    没有了
    -1.27
    それを
    -1.25
    where
    -1.25
    の場合
    -1.22
    Which
    -1.20
     первые
    -1.20
     วัน
    -1.17
    льта
    -1.16
    POSITIVE LOGITS
     voordat
    1.39
     and
    1.37
     fué
    1.27
    又不
    1.27
    </strong>
    1.26
     from
    1.20
    ('../../
    1.20
    gemini
    1.20
     veldig
    1.20
    却又
    1.19
    Activations Density 0.062%

    No Known Activations