© 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. 111844
    Prev
    Next
    INDEX
    Explanations

    short blue

    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
     burs
    0.41
    ҷ
    0.38
     our
    0.38
    やら
    0.38
     unknown
    0.38
    ध्ये
    0.37
    我们的
    0.37
     Geh
    0.37
     >>=
    0.37
    कब
    0.36
    POSITIVE LOGITS
    setHorizontal
    0.45
     khung
    0.41
    isActive
    0.40
     टै
    0.39
    itatif
    0.39
     vẫn
    0.39
     Мен
    0.38
     authenticity
    0.38
    错
    0.38
     Validity
    0.38
    Activations Density 0.000%

    No Known Activations