© 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. 7159
    Prev
    Next
    INDEX
    Explanations

    assigning and allocating values

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

    This neuron detects words related to assigning or allocating (e.g., assign, assigned, allocating, allocation).

    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
     existant
    -1.56
    </i>
    -1.45
    ⫻
    -1.38
    稹
    -1.33
    衿
    -1.33
    。“
    -1.32
    eably
    -1.31
    toContain
    -1.29
     Вт
    -1.29
     alliances
    -1.29
    POSITIVE LOGITS
    谖
    1.70
     cancelamento
    1.51
     debole
    1.36
     altrett
    1.36
     seguente
    1.36
     Welche
    1.35
     popolare
    1.34
     seguenti
    1.25
     ottimo
    1.24
     seems
    1.23
    Activations Density 0.129%

    No Known Activations