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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15177
    Prev
    Next
    INDEX
    Explanations

    programme imports

    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
     org
    0.68
     don
    0.55
     began
    0.54
     india
    0.54
     ent
    0.54
    >
    0.54
     io
    0.53
     most
    0.51
     encrypt
    0.51
     model
    0.51
    POSITIVE LOGITS
    rbrack
    0.59
    冀
    0.59
     köl
    0.56
     Unterschied
    0.53
    さが
    0.51
    Ꮂ
    0.51
     slučaju
    0.50
    Ꭾ
    0.50
     بازدید
    0.50
    弱
    0.50
    Activations Density 0.030%

    No Known Activations