© 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. 10-GEMMASCOPE-RES-131K
    7. 58718
    Prev
    Next
    INDEX
    Explanations

    enabling and assisting actions

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

    The neuron fires on words that denote giving assistance or backing (e.g. aid, abet, help, encourage, support, collude).

    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
    ╥
    -1.44
    égal
    -1.34
     sors
    -1.30
    愆
    -1.26
     CALIF
    -1.23
     determinar
    -1.22
     jenem
    -1.21
     chauss
    -1.20
    ENSIS
    -1.20
    hearted
    -1.19
    POSITIVE LOGITS
     depuis
    1.24
    目前
    1.23
     such
    1.20
    諸
    1.20
     Numerous
    1.15
    jetas
    1.12
    ;
    1.12
    öyle
    1.11
    izacion
    1.10
     authService
    1.09
    Activations Density 0.081%

    No Known Activations