© 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. 16-GEMMASCOPE-2-RES-262K
    7. 90532
    Prev
    Next
    INDEX
    Explanations

    history matching, planning, VPN, hidden

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ಾ
    0.63
    en
    0.61
    or
    0.61
    at
    0.60
    ون
    0.60
    an
    0.57
    ோ
    0.56
    is
    0.55
    im
    0.55
    ikti
    0.55
    POSITIVE LOGITS
     scoop
    0.45
     conditioner
    0.44
    中期
    0.44
     acet
    0.43
     v
    0.43
    )
    0.43
     bicycle
    0.43
    ະຍ
    0.43
     seamless
    0.42
     seat
    0.42
    Activations Density 0.000%

    No Known Activations