© 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. 28266
    Prev
    Next
    INDEX
    Explanations

    "nuts when"

    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
     legjobb
    0.51
     ajudar
    0.48
     najleps
    0.46
     lepší
    0.46
     dolayı
    0.45
     najbol
    0.45
     أ
    0.45
     consigli
    0.42
     argento
    0.42
     afbeelding
    0.41
    POSITIVE LOGITS
     filamentous
    0.48
     lineages
    0.46
    </div>
    0.42
    ensional
    0.42
    pubescens
    0.41
     lineage
    0.41
     நோய
    0.41
     fermented
    0.41
    ocytic
    0.40
    ಲಾಯಿತು
    0.40
    Activations Density 0.015%

    No Known Activations