© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127162
    Prev
    Next
    INDEX
    Explanations

    contract or event qualifying

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

    sequential selection and focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anlı
    0.47
    idad
    0.47
    ラジオ
    0.45
    iaux
    0.44
    
    0.43
    ádio
    0.43
    ansir
    0.43
    诡
    0.43
    सद
    0.42
    лів
    0.42
    POSITIVE LOGITS
     tund
    0.55
     observation
    0.54
     confidence
    0.51
     qualification
    0.49
     poll
    0.49
     mide
    0.49
     qualifying
    0.48
     Observation
    0.47
     readiness
    0.47
     manu
    0.47
    Activations Density 0.003%

    No Known Activations