© 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. 34-GEMMASCOPE-RES-131K
    7. 62854
    Prev
    Next
    INDEX
    Explanations

    onto and on

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

    The neuron strongly responds to action-oriented verbs (often in phrasal form) that describe physically manipulating or moving something.

    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
     във
    -0.80
    tria
    -0.78
    ofis
    -0.77
    ssaint
    -0.76
     vrá
    -0.75
    thet
    -0.75
    紺
    -0.75
    楣
    -0.75
     drin
    -0.74
     finalidad
    -0.73
    POSITIVE LOGITS
     onto
    8.31
    onto
    4.94
     Ont
    4.34
    Ont
    4.28
    ONTO
    3.06
     unto
    2.70
    ontological
    2.59
     lên
    2.41
     on
    2.08
     ontology
    2.06
    Activations Density 0.275%

    No Known Activations