© 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. 9914
    Prev
    Next
    INDEX
    Explanations

    scheduled events or database entries

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

    The neuron flags occurrences of domain‐specific entity or table names (e.g. Booking, Trip, Call, AssetMovement) in code and queries.

    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
     first
    -1.57
     who
    -1.47
     Inspir
    -1.46
    ortive
    -1.37
    垚
    -1.32
    最初に
    -1.32
     african
    -1.28
     when
    -1.26
     in
    -1.24
    ,:)
    -1.24
    POSITIVE LOGITS
    <bos>
    1.89
    縠
    1.64
     desnuda
    1.50
     vermeiden
    1.48
     impossível
    1.48
    了一个
    1.48
    樒
    1.46
     estranho
    1.45
    了个
    1.43
     maravilh
    1.42
    Activations Density 0.045%

    No Known Activations