© 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. 11833
    Prev
    Next
    INDEX
    Explanations

    online platforms and services

    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
    ک
    1.02
     exhaust
    0.98
     Durante
    0.98
    upuncture
    0.95
    Durante
    0.93
     Temperatura
    0.92
     دوربین
    0.91
    T
    0.91
    دت
    0.90
     taza
    0.89
    POSITIVE LOGITS
     GitLab
    0.96
    ²
    0.93
    ᾳ
    0.93
    мы
    0.93
    мов
    0.91
    zm
    0.91
     Caedwalla
    0.90
    Acts
    0.89
     armies
    0.89
    𒀀
    0.88
    Activations Density 0.132%

    No Known Activations