© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 109232
    Prev
    Next
    INDEX
    Explanations

    from X

    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_40_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
     흐
    0.47
     очень
    0.40
     mínimo
    0.39
     रिवाज
    0.38
     Россий
    0.38
     máximo
    0.38
     सम्पूर्ण
    0.38
     Tens
    0.38
     tradición
    0.38
    enhuma
    0.37
    POSITIVE LOGITS
     parenting
    0.46
    魇
    0.38
     Parenting
    0.38
    得
    0.38
    Foreign
    0.37
    asone
    0.37
     nuances
    0.36
     forState
    0.36
    Parent
    0.35
    educt
    0.35
    Activations Density 0.005%

    No Known Activations