© 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. 2126
    Prev
    Next
    INDEX
    Explanations

    alleged or unlawful actions

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

    alleged claims and disputes

    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
     nuove
    0.55
    出来る
    0.55
     neue
    0.53
     এদের
    0.52
    یم
    0.50
    د
    0.50
     ഉണ്ട്
    0.50
    ൦
    0.49
     possiamo
    0.49
     يقوم
    0.49
    POSITIVE LOGITS
     якобы
    0.80
     allegedly
    0.78
     plaintiffs
    0.74
     plaintiff
    0.70
     appellants
    0.70
     appellant
    0.70
     당시
    0.70
     unlawfully
    0.69
     complainants
    0.66
    当时
    0.65
    Activations Density 0.075%

    No Known Activations