© 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. 9076
    Prev
    Next
    INDEX
    Explanations

    local and contractual

    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
     Collaborative
    0.44
     работают
    0.43
     Karten
    0.42
     गरेको
    0.42
    梘
    0.41
     Editable
    0.40
     گرف
    0.40
    ansen
    0.40
     Donovan
    0.40
     integ
    0.40
    POSITIVE LOGITS
    хин
    0.39
    ча
    0.38
    ღ
    0.38
    금
    0.38
    Local
    0.36
     pilgrimage
    0.36
    ંજ
    0.36
    жо
    0.36
    amay
    0.36
    relay
    0.34
    Activations Density 0.001%

    No Known Activations