© 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. 2958
    Prev
    Next
    INDEX
    Explanations

    what kind of

    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
     và
    0.42
    ，
    0.42
     অর্থাৎ
    0.39
    ،
    0.39
     এবং
    0.38
    ！！！
    0.36
     describes
    0.36
    ❗️
    0.36
     ($\
    0.35
    exists
    0.35
    POSITIVE LOGITS
     также
    0.50
     zweite
    0.44
     listy
    0.43
     zusätzlich
    0.43
     आजही
    0.43
     також
    0.43
     ओपन
    0.41
     даже
    0.41
     многих
    0.40
    なども
    0.40
    Activations Density 0.103%

    No Known Activations