© 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-65K
    7. 8407
    Prev
    Next
    INDEX
    Explanations

    offering support or suggestions

    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_65k_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
    ਾਬ
    0.37
    4
    0.36
    5
    0.36
    柬
    0.35
    вара
    0.34
    
    0.34
     อ
    0.34
    фа
    0.33
     ビ
    0.33
    一
    0.33
    POSITIVE LOGITS
     rests
    0.35
     enlaces
    0.34
     lore
    0.34
     buen
    0.33
     aforementioned
    0.32
     logros
    0.31
     Gestion
    0.31
     queued
    0.31
     buon
    0.31
     Lore
    0.30
    Activations Density 0.457%

    No Known Activations