© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130407
    Prev
    Next
    INDEX
    Explanations

    create or modify

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

    The neuron fires strongly on verbs that denote creating, updating, or otherwise modifying something (e.g. create, update, modify, reinstall, enhance).

    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
     ľudí
    -1.38
    Either
    -1.24
    anes
    -1.20
     electrónicos
    -1.16
    很喜欢
    -1.14
    するか
    -1.13
     princí
    -1.12
    赡
    -1.12
    </h3>
    -1.11
    tamente
    -1.09
    POSITIVE LOGITS
     already
    1.46
     allerede
    1.18
     these
    1.15
    の状態
    1.13
     our
    1.09
     not
    1.09
     уже
    1.06
     regista
    1.05
     so
    1.02
     bū
    1.02
    Activations Density 0.065%

    No Known Activations