© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8865
    Prev
    Next
    INDEX
    Explanations

    focus on

    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
     things
    0.73
     something
    0.68
     κάτι
    0.64
     شيء
    0.63
     stuff
    0.62
     really
    0.61
     Something
    0.61
    。
    0.60
     someth
    0.59
     Things
    0.59
    POSITIVE LOGITS
     extensively
    0.98
     العديد
    0.80
     преимущественно
    0.79
     numerose
    0.78
     numerous
    0.77
     principalement
    0.77
     számos
    0.76
     variously
    0.75
     numerosi
    0.75
     zahlreiche
    0.75
    Activations Density 0.092%

    No Known Activations