© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9272
    Prev
    Next
    INDEX
    Explanations

    explanation text

    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_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     pouquinho
    0.71
    <sub>
    0.70
     そして
    0.67
     (!)
    0.64
    (!)
    0.63
     ensues
    0.63
    煂
    0.63
     வகையான
    0.62
     वैशिष्ट
    0.62
    😑
    0.61
    POSITIVE LOGITS
    ци
    0.70
    क
    0.66
    e
    0.65
    cip
    0.63
     क़
    0.62
    pload
    0.61
    ка
    0.61
    дно
    0.59
    cello
    0.59
    tuning
    0.59
    Activations Density 0.946%

    No Known Activations