© 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-262K
    7. 26149
    Prev
    Next
    INDEX
    Explanations

    corner and common subsequent words

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Surfaces
    0.43
     Directories
    0.41
     surfaces
    0.40
     sings
    0.39
     wave
    0.38
     siblings
    0.38
     DISTINCT
    0.37
    闓
    0.37
    MOV
    0.36
     Interchange
    0.35
    POSITIVE LOGITS
     corner
    1.00
    corner
    0.96
    Corner
    0.92
     Corner
    0.89
     esquina
    0.85
     कोने
    0.82
     corners
    0.77
    角落
    0.75
    角
    0.72
     nook
    0.70
    Activations Density 0.004%

    No Known Activations