© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34860
    Prev
    Next
    INDEX
    Explanations

    decided to do something

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

    The neuron fires strongly on content verbs (main action words) – especially infinitives or simple verbs that describe doing or deciding to do 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_22/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
    多次
    -1.29
     jeweiligen
    -1.14
     lograr
    -1.14
     required
    -1.13
     want
    -1.12
     erfolgreichen
    -1.06
     estrenar
    -1.05
     needed
    -1.05
     distintas
    -1.01
     containing
    -1.00
    POSITIVE LOGITS
     rather
    1.59
     instead
    1.53
    rather
    1.39
    を購入
    1.36
    instead
    1.29
    而不是
    1.25
     piuttosto
    1.20
     דו
    1.16
     MÉ
    1.15
     plutôt
    1.13
    Activations Density 0.031%

    No Known Activations