© 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-16K
    7. 14063
    Prev
    Next
    INDEX
    Explanations

    relationship between 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
    场景
    0.42
     scene
    0.38
     پردا
    0.37
     comboBox
    0.37
    </li>
    0.36
     免
    0.36
    免
    0.36
    <0xC2>
    0.35
     меди
    0.35
     надо
    0.35
    POSITIVE LOGITS
    齬
    0.44
     Küchen
    0.41
     clerg
    0.41
     Hrvatske
    0.41
    渾
    0.41
     भरे
    0.40
    陬
    0.39
    шло
    0.39
     purpos
    0.39
     Polizei
    0.39
    Activations Density 0.002%

    No Known Activations