© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 11894
    Prev
    Next
    INDEX
    Explanations

    what a process is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    or
    0.82
    ile
    0.75
    in
    0.68
    '
    0.67
    ot
    0.65
    the
    0.63
    .
    0.63
    بی
    0.60
    き
    0.60
     بی
    0.59
    POSITIVE LOGITS
     процесс
    1.08
     процессы
    1.06
     processes
    1.04
    过程
    1.03
     process
    1.02
     Processes
    0.98
     Proces
    0.96
     Process
    0.93
     과정을
    0.92
     Prozesse
    0.91
    Activations Density 0.227%

    No Known Activations