© 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. 5936
    Prev
    Next
    INDEX
    Explanations

    memory units

    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
     dispersion
    0.59
    彫
    0.57
     souten
    0.57
     Dispersion
    0.56
    nail
    0.53
     укреп
    0.51
    anim
    0.50
     Plush
    0.50
    ControlType
    0.49
    Ρ
    0.49
    POSITIVE LOGITS
     kilobytes
    0.77
     memory
    0.76
    缓冲区
    0.71
     pageSize
    0.71
     buffer
    0.70
     mémoire
    0.70
    BufferSize
    0.70
     memória
    0.69
     Memory
    0.67
    内存
    0.66
    Activations Density 0.486%

    No Known Activations