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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65970
    Prev
    Next
    INDEX
    Explanations

    property proposals

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

    The neuron detects language that introduces or describes proposed plans or projects (e.g. “proposed,” “slated for,” “is planning,” “plans to…”).

    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
     especially
    -1.20
     takich
    -1.18
     lesiones
    -1.08
     infecciones
    -1.06
    Otros
    -1.05
    odynamic
    -1.05
     even
    -1.05
     අ
    -1.05
     important
    -1.04
     každé
    -1.02
    POSITIVE LOGITS
     ранее
    1.23
     naselje
    1.20
    uden
    1.16
    ̋
    1.15
     menghadirkan
    1.15
     Վերցված
    1.14
    áles
    1.13
     oreille
    1.12
    mspace
    1.12
    ల్
    1.12
    Activations Density 0.019%

    No Known Activations