© 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. 193744
    Prev
    Next
    INDEX
    Explanations

    health, injury, physical, detailed care

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

    testing limits

    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
    탉
    0.59
    ギリス
    0.52
    ുമ്പോൾ
    0.52
     시대
    0.51
    지가
    0.50
    푞
    0.50
    湆
    0.50
     misfortunes
    0.49
    㱛
    0.49
    लता
    0.49
    POSITIVE LOGITS
     of
    0.49
    1
    0.49
     bestimmten
    0.46
     N
    0.46
     this
    0.45
      
    0.45
     Bridge
    0.44
     A
    0.44
     some
    0.44
     certain
    0.43
    Activations Density 0.000%

    No Known Activations