© 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. 22-GEMMASCOPE-RES-131K
    4. 13792
    Prev
    Next
    INDEX
    Explanations

    role or function

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

    The neuron flags high‐level methodological or goal‐oriented research terms (e.g. determine, active participation, information retrieval) typically found in scientific proposals.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     that
    -1.23
     when
    -1.04
     поэтому
    -1.02
     which
    -0.97
    adoras
    -0.89
     this
    -0.86
     caratteri
    -0.85
    pertoire
    -0.83
     acepción
    -0.82
     where
    -0.81
    POSITIVE LOGITS
     and
    2.73
    ทั้ง
    1.09
     både
    1.09
    yons
    1.08
    力和
    1.07
    barber
    1.04
    presa
    1.01
    salomon
    1.00
     zowel
    0.99
    venus
    0.99
    Activations Density 0.127%

    No Known Activations