© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 34490
    Prev
    Next
    INDEX
    Explanations

    social networks and media

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ósitos
    1.04
     이하
    1.02
    ний
    1.01
    тата
    0.99
    itats
    0.96
    igo
    0.95
    ното
    0.95
    ]')
    0.94
    كذا
    0.93
    ﻧ
    0.93
    POSITIVE LOGITS
     feud
    1.31
    まるで
    1.14
     sociales
    1.11
     wreath
    1.10
     turmoil
    1.10
     limelight
    1.10
    అ
    1.09
    如同
    1.07
    こんばんは
    1.07
     enumerable
    1.05
    Activations Density 0.029%

    No Known Activations