© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7291
    Prev
    Next
    INDEX
    Explanations

    analysis of topics

    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_16k_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
     उस
    0.46
    无
    0.45
    ಿತ್ತು
    0.43
     সেই
    0.41
    iul
    0.41
    与
    0.41
    無
    0.40
    そのような
    0.39
    那位
    0.38
    쿄
    0.38
    POSITIVE LOGITS
     analysis
    0.41
     discussion
    0.41
     pylori
    0.39
     Discussion
    0.38
     homenagem
    0.37
     restent
    0.37
     conseils
    0.37
     aktivit
    0.37
     markers
    0.36
     panor
    0.36
    Activations Density 0.312%

    No Known Activations