© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 47656
    Prev
    Next
    INDEX
    Explanations

    complexity and inherent nature

    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
     절
    0.40
    匿
    0.40
     추
    0.39
    観察
    0.39
    {(\
    0.38
    𝐛
    0.38
    buffer
    0.38
    Cancer
    0.38
    anted
    0.38
     selectors
    0.37
    POSITIVE LOGITS
    ancio
    0.39
     मुखिया
    0.39
     Generale
    0.38
     scooped
    0.37
    mittedly
    0.36
    எ
    0.36
     worried
    0.36
     قائد
    0.36
     menos
    0.36
    kem
    0.35
    Activations Density 0.008%

    No Known Activations