© 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. 29743
    Prev
    Next
    INDEX
    Explanations

    steps and procedures

    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
    expressions
    0.40
    consciousness
    0.39
    /**/*.
    0.38
     fenó
    0.38
     रोगों
    0.38
     considerando
    0.37
     réactions
    0.37
     વ્ય
    0.36
    碍
    0.36
    ভূমির
    0.36
    POSITIVE LOGITS
    步驟
    0.98
    手順
    0.96
     steps
    0.88
    步骤
    0.88
     Procedure
    0.88
     Steps
    0.88
     procedure
    0.87
     Step
    0.82
    Procedure
    0.82
     step
    0.80
    Activations Density 0.753%

    No Known Activations