© 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. 24-GEMMASCOPE-2-RES-16K
    7. 5773
    Prev
    Next
    INDEX
    Explanations

    address, key, format, type, number, structure

    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_24_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ለአ
    0.67
     මේ
    0.63
     للأ
    0.58
    ımızın
    0.57
     triun
    0.54
     først
    0.54
     لأ
    0.52
     turbulent
    0.52
     avanç
    0.52
     ל
    0.52
    POSITIVE LOGITS
    飩
    0.68
     англий
    0.65
     Великобрита
    0.65
    shakespeare
    0.64
    ματος
    0.63
    ולנד
    0.62
    ailles
    0.62
    akespeare
    0.61
     евре
    0.60
    拉斯
    0.59
    Activations Density 0.002%

    No Known Activations