© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59158
    Prev
    Next
    INDEX
    Explanations

    developed into a

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

    The neuron fires on the preposition “into,” especially in developmental or transformational phrases (e.g. “evolved into,” “developed into”).

    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
     on
    -2.17
     to
    -2.11
     at
    -1.91
     within
    -1.60
     as
    -1.60
     or
    -1.60
     time
    -1.59
     there
    -1.48
     before
    -1.45
     while
    -1.44
    POSITIVE LOGITS
     verrou
    1.76
     doivent
    1.73
     objectifs
    1.71
     semelh
    1.70
    一个
    1.62
     moteurs
    1.60
     payé
    1.59
     défis
    1.59
     ouverture
    1.58
     khoe
    1.56
    Activations Density 0.019%

    No Known Activations