© 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. 40-GEMMASCOPE-2-RES-16K
    7. 12410
    Prev
    Next
    INDEX
    Explanations

    behind

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ெட்
    0.41
    ન્સ
    0.40
     doloribus
    0.39
    াবাহ
    0.38
    vedad
    0.38
    ెస్
    0.37
    KEYS
    0.36
    鳧
    0.36
    }^{*}\
    0.35
    먼
    0.35
    POSITIVE LOGITS
     behind
    1.52
     Behind
    1.48
    Behind
    1.45
    behind
    1.35
     detrás
    1.23
     derrière
    1.13
     dietro
    1.09
     atrás
    0.93
     پشت
    0.88
     curtain
    0.87
    Activations Density 0.072%

    No Known Activations