© 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-16K
    4. 791
    Prev
    Next
    INDEX
    Explanations

    z words

    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
     William
    0.46
    William
    0.43
     Nederlandse
    0.39
     Mga
    0.39
    বাংলাদেশের
    0.39
    Richard
    0.38
    இந்திய
    0.38
    ས
    0.38
    The
    0.37
    تح
    0.37
    POSITIVE LOGITS
     thawed
    0.38
     heterogeneity
    0.37
     parameter
    0.37
     fluctuation
    0.36
     hazards
    0.35
     fallback
    0.34
     jargon
    0.33
     decre
    0.33
     rates
    0.33
     heatmap
    0.33
    Activations Density 0.110%

    No Known Activations