© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51926
    Prev
    Next
    INDEX
    Explanations

    utility, constraint, friends, spheres, str

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wik
    0.48
    ни
    0.46
     defendant
    0.45
     perpetrated
    0.45
     due
    0.44
     pumping
    0.44
    u
    0.44
    urende
    0.43
    افظ
    0.43
     oleh
    0.43
    POSITIVE LOGITS
    Dates
    0.48
     WAIT
    0.45
    瞩
    0.43
    最重要的
    0.42
    引领
    0.42
    
    0.42
    Princ
    0.42
     เม
    0.41
    Styl
    0.41
     एडवा
    0.41
    Activations Density 0.006%

    No Known Activations