© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11836
    Prev
    Next
    INDEX
    Explanations

    processes and transitions

    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_262k_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
    maxage
    0.41
    w
    0.39
    的に
    0.39
    z
    0.38
     amends
    0.38
     bouw
    0.38
     خوشه
    0.38
     Mackey
    0.38
     ඒවා
    0.37
     ത
    0.36
    POSITIVE LOGITS
     işlemi
    0.51
     erfolgen
    0.51
     avven
    0.45
     procesu
    0.45
     happening
    0.45
     occurring
    0.44
     करण्याचा
    0.44
     процессе
    0.43
    過程中
    0.42
     ceremony
    0.41
    Activations Density 0.134%

    No Known Activations