© 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. 31-GEMMASCOPE-2-RES-65K
    7. 27184
    Prev
    Next
    INDEX
    Explanations

    north, not, or special cases

    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
    ون
    0.45
     lockdowns
    0.44
    राय
    0.44
     extremism
    0.44
     photons
    0.43
     प्रेरणा
    0.43
    ทย์
    0.43
    药
    0.42
     gurus
    0.42
     टाइम
    0.42
    POSITIVE LOGITS
    ète
    0.45
     Découvrez
    0.44
     tind
    0.44
    )(-
    0.43
    érm
    0.43
    ères
    0.43
     neighbour
    0.42
    conjugated
    0.42
    ase
    0.41
    cije
    0.41
    Activations Density 0.006%

    No Known Activations