© 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. 5244
    Prev
    Next
    INDEX
    Explanations

    ability to perform actions

    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
    რო
    0.58
    അ
    0.56
    ام
    0.54
    allow
    0.54
     கொள்ளலாம்
    0.53
    observable
    0.51
    Μ
    0.50
    да
    0.50
    ಡೆ
    0.50
    ้าย
    0.50
    POSITIVE LOGITS
     afford
    0.64
     discern
    0.60
     withstand
    0.59
     identify
    0.57
     muster
    0.50
     Identify
    0.48
     document
    0.47
     speak
    0.46
     name
    0.46
     afforded
    0.46
    Activations Density 0.192%

    No Known Activations