© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 51910
    Prev
    Next
    INDEX
    Explanations

    important notes

    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_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
     പ്രത്യേക
    0.45
     preocupaciones
    0.43
     मध्य
    0.39
     limitaciones
    0.38
     financière
    0.37
     thách
    0.37
    worthy
    0.36
    <0xB6>
    0.36
     sécrétion
    0.35
     appla
    0.35
    POSITIVE LOGITS
     Instructions
    0.68
     instructions
    0.67
    Instructions
    0.63
    instructions
    0.63
     инструк
    0.55
     Anleitung
    0.55
     instruct
    0.54
     instruções
    0.54
     instrucciones
    0.51
     инструкции
    0.51
    Activations Density 0.023%

    No Known Activations