© 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. 120890
    Prev
    Next
    INDEX
    Explanations

    higher income or percentage

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

    unethical or philosophical consequences

    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
    南方
    0.47
    as
    0.44
    此
    0.44
    南部
    0.41
     promoter
    0.41
    INAL
    0.39
    賀
    0.38
    再
    0.38
     accessory
    0.38
    衞
    0.37
    POSITIVE LOGITS
    defeated
    0.55
    sframe
    0.52
     Mecklenburg
    0.50
     Informationen
    0.47
     Anleitung
    0.47
     Informasi
    0.46
     కోట్ల
    0.46
    çoivent
    0.46
     informée
    0.46
    શ્વ
    0.45
    Activations Density 0.000%

    No Known Activations