© 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-65K
    7. 30142
    Prev
    Next
    INDEX
    Explanations

    programming syntax and symbols

    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
     While
    0.31
        
    0.29
    os
    0.28
    other
    0.28
     The
    0.28
     sure
    0.28
    i
    0.28
     Veteran
    0.27
    io
    0.26
     Due
    0.26
    POSITIVE LOGITS
     hydroly
    0.29
     cannabinoids
    0.28
    CCOCC
    0.28
     pyrid
    0.28
     hydroxyl
    0.28
    細胞
    0.26
    Pyrazole
    0.26
     epoxide
    0.26
     ه
    0.26
     細胞
    0.26
    Activations Density 0.189%

    No Known Activations