© 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. 74845
    Prev
    Next
    INDEX
    Explanations

    . you

    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
    當
    0.45
     visitas
    0.45
    제
    0.45
     regulación
    0.45
    ين
    0.43
    يين
    0.43
    ::__
    0.42
    ေ
    0.42
    N
    0.41
    édéric
    0.41
    POSITIVE LOGITS
     microbes
    0.42
     kicks
    0.42
    sah
    0.42
     fronts
    0.41
     universes
    0.41
     Screens
    0.40
    បំផុត
    0.40
     Mathf
    0.40
     metals
    0.40
     خاصة
    0.40
    Activations Density 0.006%

    No Known Activations