© 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. 85034
    Prev
    Next
    INDEX
    Explanations

    emerged as

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

    The main thing this neuron does is find occurrences of “emerge” and its derivatives (e.g., emerged, emergence, emerging).

    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
    訁
    -2.72
    you
    -2.63
    
    -2.34
    埽
    -2.31
    at
    -2.30
    for
    -2.20
    also
    -2.16
    ￬
    -2.14
    衽
    -2.11
    ícias
    -2.05
    POSITIVE LOGITS
     from
    1.92
     –
    1.88
    ;
    1.76
    彀
    1.75
     tulee
    1.75
     Each
    1.72
    他
    1.71
     burgeoning
    1.70
    然后
    1.68
    ཫ
    1.67
    Activations Density 0.022%

    No Known Activations