© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 218019
    Prev
    Next
    INDEX
    Explanations

    numbers and text following them

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

    * non-cutting

    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
    Negative Logits
     ಅಥವಾ
    0.62
     அல்லது
    0.59
     లేదా
    0.57
     または
    0.55
    または
    0.54
     じゃん
    0.54
     或
    0.54
     espalda
    0.51
     நிறைந்த
    0.51
     点
    0.51
    POSITIVE LOGITS
     DR
    0.45
    haz
    0.43
    ្នុង
    0.43
    approx
    0.41
    slee
    0.40
     examiner
    0.40
    Well
    0.39
     kece
    0.39
    blur
    0.39
    Ignore
    0.38
    Activations Density 0.001%

    No Known Activations