© 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. 240370
    Prev
    Next
    INDEX
    Explanations

    indemnify, defend, hold harmless, officers, subsidiaries

    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
     контро
    0.51
    f
    0.50
     kunde
    0.50
     fått
    0.49
     hilft
    0.48
    ebi
    0.47
     entdeckt
    0.47
     när
    0.47
     eğit
    0.46
     bekam
    0.46
    POSITIVE LOGITS
    訌
    0.46
    ｣
    0.43
     CEOs
    0.43
    ામ
    0.42
    當然
    0.42
    夂
    0.42
    饨
    0.42
    惀
    0.42
    乙
    0.41
    妧
    0.39
    Activations Density 0.001%

    No Known Activations