© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14289
    Prev
    Next
    INDEX
    Explanations

    contrast and comparison

    np_acts-logits-general · gemini-2.5-flash-lite

    open versus closed distinction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    狱
    0.38
    =#
    0.36
    ależy
    0.36
    jhelp
    0.36
    actionBar
    0.35
    আত্ম
    0.35
    ላቸው
    0.35
     لهم
    0.34
    ="
    0.34
    ைகள்
    0.34
    POSITIVE LOGITS
     unlike
    2.27
    unlike
    2.09
     Unlike
    2.03
    Unlike
    1.91
     contrairement
    1.87
    不像
    1.63
     отличие
    1.38
    whereas
    1.38
     Whereas
    1.34
     whereas
    1.33
    Activations Density 0.656%

    No Known Activations