© 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. 22-GEMMASCOPE-RES-131K
    7. 25553
    Prev
    Next
    INDEX
    Explanations

    drag and drop actions

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

    The neuron fires on occurrences of the word “drag” or “dragging,” i.e. mentions of drag‐and‐drop interactions.

    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
     fiables
    -1.09
     verdo
    -1.06
    loyal
    -1.05
    画家
    -1.05
     eficientes
    -1.01
    好像
    -1.00
    有很多
    -0.99
    ∷
    -0.98
    lative
    -0.98
    youth
    -0.98
    POSITIVE LOGITS
     przen
    1.16
     leçon
    1.13
    ﻻ
    1.10
     lucrative
    1.09
     bedoeld
    1.09
     truco
    1.08
     cargas
    1.05
    otonin
    1.04
    看着他
    1.04
     cerrado
    1.03
    Activations Density 0.014%

    No Known Activations