© 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. 106867
    Prev
    Next
    INDEX
    Explanations

    phrases linking concepts

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

    traditional data methods

    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
     gerade
    0.50
    ayı
    0.49
    Impl
    0.48
    哀
    0.48
     svoje
    0.47
     mystical
    0.47
    首先
    0.46
    ۇ
    0.46
    Saya
    0.45
    পত
    0.45
    POSITIVE LOGITS
     উত্তোলন
    0.49
     lemmas
    0.46
     lifting
    0.45
     turma
    0.45
     opin
    0.44
     opinions
    0.44
     нашем
    0.44
     эксплуатации
    0.43
     అధికారు
    0.42
     Lifting
    0.41
    Activations Density 0.000%

    No Known Activations