© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15898
    Prev
    Next
    INDEX
    Explanations

    attempting 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_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
    gamer
    0.50
     geboren
    0.48
     hist
    0.45
    January
    0.44
    lib
    0.42
    sock
    0.42
    ()->
    0.42
    Elig
    0.42
     remanded
    0.41
    pFile
    0.41
    POSITIVE LOGITS
    狒
    0.52
     subgraph
    0.48
     Motions
    0.48
    𝗨
    0.47
     Automatic
    0.47
     डेमो
    0.47
     Operations
    0.46
     Testing
    0.46
     Aeronautics
    0.46
     kuchh
    0.46
    Activations Density 0.004%

    No Known Activations