© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9731
    Prev
    Next
    INDEX
    Explanations

    AI model self-description

    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
    Negative Logits
    want
    0.43
    our
    0.42
     queremos
    0.41
    想
    0.40
    覺得
    0.39
    å
    0.39
     piensan
    0.38
     naszej
    0.38
    thoughts
    0.38
    希望
    0.37
    POSITIVE LOGITS
     operates
    0.45
     infrast
    0.40
     undergoes
    0.39
    수가
    0.38
     deuterium
    0.38
    ;
    0.38
     встроен
    0.37
    zelf
    0.37
    的情况
    0.37
     GPT
    0.36
    Activations Density 0.158%

    No Known Activations