© 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-16K
    7. 2008
    Prev
    Next
    INDEX
    Explanations

    if you

    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_16k_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
    ennzeichnet
    0.50
     ಪ್ರಯೋಜನ
    0.50
    וס
    0.49
     फिटनेस
    0.49
     लेबल
    0.48
    盞
    0.47
     గేమ్
    0.47
     RULES
    0.46
     দুঃ
    0.46
    Bechyné
    0.46
    POSITIVE LOGITS
    0.52
    ↵↵
    0.51
     already
    0.51
     two
    0.48
     legitimately
    0.47
     kind
    0.44
     genuinely
    0.44
     both
    0.44
     well
    0.43
      
    0.43
    Activations Density 0.005%

    No Known Activations