© 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. 80741
    Prev
    Next
    INDEX
    Explanations

    our product/service descriptions

    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
     postpon
    0.52
     phosphory
    0.44
     partialX
    0.44
     metastability
    0.42
     complejidad
    0.42
    ovna
    0.42
     problemat
    0.42
    abhavena
    0.41
     podendo
    0.41
    ଭ
    0.41
    POSITIVE LOGITS
     flagship
    0.50
     مجموعه
    0.50
     collection
    0.50
     Sammlung
    0.49
     recommendation
    0.48
     advice
    0.48
     Collection
    0.48
     infographic
    0.48
     illustration
    0.47
     Guide
    0.46
    Activations Density 0.010%

    No Known Activations