© 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-65K
    7. 56588
    Prev
    Next
    INDEX
    Explanations

    ascending order by suit

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ו
    0.59
    Ha
    0.57
    .??.??"]
    0.57
    Pes
    0.49
    ≙
    0.48
    Been
    0.47
    Comp
    0.47
    Messi
    0.47
    RMSE
    0.47
    Há
    0.47
    POSITIVE LOGITS
     penyakit
    0.47
     instances
    0.46
    imer
    0.44
     seats
    0.44
     infections
    0.44
     subscriptions
    0.44
    ultura
    0.44
    istik
    0.44
     suits
    0.43
    徝
    0.43
    Activations Density 0.002%

    No Known Activations