© 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. 128941
    Prev
    Next
    INDEX
    Explanations

    unique products

    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
    Not in Any Lists

    No Comments

    Negative Logits
    रेखा
    0.48
     myel
    0.47
     multitudes
    0.47
     idioma
    0.47
     ă
    0.45
     responsables
    0.45
     idiomas
    0.45
     antidepressants
    0.44
     gasped
    0.44
     merken
    0.44
    POSITIVE LOGITS
    aranteed
    0.41
    ex
    0.41
    completely
    0.37
    only
    0.35
    Original
    0.35
    **
    0.34
    original
    0.33
    Available
    0.33
    reflect
    0.33
    shift
    0.33
    Activations Density 0.005%

    No Known Activations