© 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-16K
    7. 11588
    Prev
    Next
    INDEX
    Explanations

    describing personal feelings or states

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     стрелецкой
    1.10
    沩
    1.03
     potentialities
    0.92
    시켜
    0.91
     tentativo
    0.90
    交易
    0.90
     conviv
    0.90
    等待
    0.89
    សម្រាប់
    0.89
     tempus
    0.89
    POSITIVE LOGITS
    1
    1.16
     هذا
    1.05
     this
    1.01
    2
    0.97
     ebben
    0.94
     اين
    0.93
    et
    0.93
    yy
    0.92
     सड़कें
    0.91
     این
    0.91
    Activations Density 0.188%

    No Known Activations