© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1806
    Prev
    Next
    INDEX
    Explanations

    break/organize then this/it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝓂
    0.70
     lets
    0.58
     realiza
    0.55
    りで
    0.55
     beraber
    0.54
     در
    0.53
     guess
    0.53
     ds
    0.53
     preface
    0.52
     ।
    0.52
    POSITIVE LOGITS
     এটাকে
    0.98
     it
    0.95
     them
    0.95
     এটিকে
    0.90
     इसे
    0.89
    them
    0.86
    它
    0.84
    มัน
    0.82
     이를
    0.80
     તેને
    0.78
    Activations Density 0.286%

    No Known Activations