© 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. 192139
    Prev
    Next
    INDEX
    Explanations

    vertical and related directions

    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
    ](\
    0.41
    傚
    0.40
    っても
    0.40
    மாறு
    0.38
     désormais
    0.38
    exploitation
    0.38
    矛
    0.38
    ከተ
    0.37
     outlets
    0.37
    成了
    0.37
    POSITIVE LOGITS
     Vertical
    0.61
    Vertical
    0.60
     vertical
    0.59
    vertical
    0.59
     vertically
    0.52
     вертика
    0.51
     verticales
    0.49
    垂直
    0.44
    VERTICAL
    0.44
     horizontal
    0.42
    Activations Density 0.003%

    No Known Activations