© 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. 48620
    Prev
    Next
    INDEX
    Explanations

    algorithm and indices

    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
    the
    0.45
    कह
    0.43
     Ayala
    0.42
    Stre
    0.42
    respon
    0.41
     aumentada
    0.41
    gall
    0.40
    stre
    0.40
     issn
    0.40
    )}(
    0.39
    POSITIVE LOGITS
     vetting
    0.49
     salió
    0.49
     nommé
    0.46
     teníamos
    0.46
     dépour
    0.46
     lieux
    0.46
     swapping
    0.45
    znych
    0.45
     Saturday
    0.44
     doodle
    0.43
    Activations Density 0.001%

    No Known Activations