© 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. 9230
    Prev
    Next
    INDEX
    Explanations

    degree of polynomials

    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
    Not in Any Lists

    No Comments

    Negative Logits
    }:
    0.63
     Internal
    0.62
     Cultures
    0.62
    },
    0.61
     dv
    0.61
    ।
    0.61
     Iso
    0.60
     Ner
    0.59
     Livraison
    0.59
    Inner
    0.58
    POSITIVE LOGITS
    quia
    0.58
     высокого
    0.57
    års
    0.56
    म्मू
    0.53
     اقدامات
    0.53
    ेंटल
    0.52
    ovaných
    0.52
     خان
    0.51
     童
    0.51
    ാൻഡ്
    0.51
    Activations Density 0.001%

    No Known Activations