© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50051
    Prev
    Next
    INDEX
    Explanations

    manner so as to

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

    The neuron fires on the main action verbs and function words in procedural or how-to solution steps—i.e. those “do this,” “make it so,” “translate into,” “selected by,” “design a scheme” style phrases.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Tämä
    -1.07
    jecture
    -1.06
     anstatt
    -1.05
     које
    -1.01
     omdat
    -1.01
     valioso
    -1.01
     女孩
    -1.00
    ponible
    -1.00
     recomendado
    -0.99
     usamos
    -0.99
    POSITIVE LOGITS
     so
    5.69
     such
    5.28
     כך
    3.44
    such
    3.34
     так
    3.31
     таким
    3.28
     sehingga
    3.00
    Such
    2.88
     така
    2.86
     настолько
    2.84
    Activations Density 0.285%

    No Known Activations