© 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. 41532
    Prev
    Next
    INDEX
    Explanations

    active state or component

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

    This neuron detects occurrences of the adjective “active” when used in technical or scientific contexts (e.g., “active regions,” “active catalyst,” “active sites”).

    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
    3
    -1.20
    培训
    -1.18
     beide
    -1.16
     Priv
    -1.13
    vaded
    -1.12
     erg
    -1.11
    elsch
    -1.10
    纽
    -1.08
     acceso
    -1.08
    Comes
    -1.05
    POSITIVE LOGITS
     entanto
    1.27
    ումներ
    1.27
     soñar
    1.25
    امية
    1.24
     that
    1.24
     pouze
    1.23
    Pozri
    1.23
    sbereich
    1.22
    偸
    1.20
     muchísimo
    1.20
    Activations Density 0.112%

    No Known Activations