© 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-65K
    7. 44811
    Prev
    Next
    INDEX
    Explanations

    access permissions and controls

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     narratives
    0.52
     thermometers
    0.51
     imaging
    0.48
     atl
    0.47
     broth
    0.47
     algorit
    0.46
     furnaces
    0.46
    熱
    0.46
     vibr
    0.46
     antidepressants
    0.46
    POSITIVE LOGITS
    权限
    1.16
     permissions
    0.99
     Permissions
    0.99
    Permissions
    0.95
    permissions
    0.93
    授权
    0.89
    Permission
    0.87
    授予
    0.87
     Permission
    0.82
     granting
    0.80
    Activations Density 0.175%

    No Known Activations