© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70696
    Prev
    Next
    INDEX
    Explanations

    states or consequences

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

    The neuron detects words and phrases denoting bureaucratic or political actions, errors, or maneuvers.

    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
    probably
    -1.43
     Irlanda
    -1.32
     probablement
    -1.31
     marea
    -1.31
     wahrscheinlich
    -1.28
     pirata
    -1.27
     regalar
    -1.24
     sûrement
    -1.23
    gether
    -1.19
     durer
    -1.18
    POSITIVE LOGITS
     or
    2.64
     more
    1.88
     as
    1.87
     with
    1.73
     some
    1.60
    veja
    1.40
     profundos
    1.38
     svært
    1.35
     considerazione
    1.34
     administrativos
    1.34
    Activations Density 0.319%

    No Known Activations