© 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. 10-GEMMASCOPE-RES-131K
    7. 13324
    Prev
    Next
    INDEX
    Explanations

    it is ... to phrases

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

    The neuron fires on evaluative or emphatic discourse markers—especially “It’s … to …” and “It’s … that …” phrases (e.g. “It’s important to,” “It’s easy to assume,” “It’s clear that,” etc.) signaling advice or opinion.

    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
    ”
    -2.28
    ;
    -1.90
    ”.
    -1.89
    :
    -1.88
     other
    -1.87
     what
    -1.71
     its
    -1.67
     is
    -1.61
    ”,
    -1.60
    ....
    -1.59
    POSITIVE LOGITS
     however
    1.97
    Namun
    1.92
     inoltre
    1.90
     όμως
    1.85
    Kemudian
    1.69
    Mereka
    1.67
     therefore
    1.61
     then
    1.60
    それでは
    1.58
    Tapi
    1.56
    Activations Density 0.357%

    No Known Activations