© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138028
    Prev
    Next
    INDEX
    Explanations

    vibe check

    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_262k_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
    function
    0.46
    really
    0.45
    funciones
    0.44
    s
    0.43
     LOD
    0.43
     partes
    0.43
    लया
    0.41
     class
    0.41
     function
    0.41
     optimism
    0.40
    POSITIVE LOGITS
    쯤
    0.48
    MyToolkit
    0.43
    类似的
    0.42
    ्योपै
    0.42
    連合
    0.42
    නු
    0.41
    内核
    0.41
    EventRecorder
    0.40
    শিশু
    0.40
    淦
    0.40
    Activations Density 0.010%

    No Known Activations