© 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. 9311
    Prev
    Next
    INDEX
    Explanations

    predicting outcomes

    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
     തന്റെ
    0.61
     कराने
    0.60
     проєкту
    0.58
    抵达
    0.58
    constructor
    0.58
    မ္
    0.58
    prés
    0.57
     menjalani
    0.57
    ⁠
    0.57
    challenged
    0.56
    POSITIVE LOGITS
     결방
    0.72
     kita
    0.71
     unbiased
    0.68
     predict
    0.65
     केजरीवाल
    0.65
     कमजोरी
    0.62
     Kejriwal
    0.62
     Buhari
    0.61
     Watching
    0.61
     vores
    0.61
    Activations Density 0.040%

    No Known Activations