© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103086
    Prev
    Next
    INDEX
    Explanations

    postulate or postulate that

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

    The neuron fires most strongly on the verb “postulate” (and its inflected forms), i.e. on language where the text is stating or proposing a hypothesis.

    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
     unſ
    -2.81
    都能
    -2.81
     we
    -2.73
     και
    -2.64
    where
    -2.58
     où
    -2.50
    ⢌
    -2.50
    and
    -2.36
     uſed
    -2.27
    。
    -2.27
    POSITIVE LOGITS
    _{
    2.41
     она
    2.39
     econó
    2.36
    伱
    2.33
     restroom
    2.28
    人たち
    2.27
    我们
    2.23
     We
    2.23
     intrigue
    2.23
    );
    2.19
    Activations Density 0.033%

    No Known Activations