© 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. 10-GEMMASCOPE-RES-131K
    7. 41883
    Prev
    Next
    INDEX
    Explanations

    onto a surface or destination

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

    The main thing this neuron does is detect the word “onto.”

    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
     was
    -3.16
    .
    -2.47
    <bos>
    -2.38
     is
    -2.34
     titel
    -2.30
    ");
    -2.25
    ляют
    -2.23
     He
    -2.16
    将来
    -2.16
     can
    -2.00
    POSITIVE LOGITS
     whom
    2.77
    ⸂
    2.58
    刂
    2.50
    轳
    2.44
     THROUGH
    2.44
    𖣘
    2.42
     WHILE
    2.41
     drenched
    2.39
    傒
    2.38
    zembro
    2.33
    Activations Density 0.007%

    No Known Activations