© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 277
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     assumes
    0.67
    autre
    0.64
    ulous
    0.63
     sold
    0.62
     Glass
    0.60
     Large
    0.60
    ulents
    0.59
     We
    0.59
     Assume
    0.59
    @
    0.59
    POSITIVE LOGITS
     how
    2.25
     why
    2.15
     what
    2.12
    why
    2.09
     cómo
    2.05
     waarom
    1.92
    what
    1.89
     WHY
    1.80
    為什麼
    1.77
     whats
    1.75
    Activations Density 7.861%

    No Known Activations