© 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-65K
    7. 4506
    Prev
    Next
    INDEX
    Explanations

    identifying descriptions of states or conditions

    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
    TempBuffer
    0.51
    โร
    0.49
     postérieur
    0.48
    <unused226>
    0.48
     mermaid
    0.48
    +{\
    0.48
    私募基金
    0.47
    耶稣
    0.47
     paediatric
    0.46
     pediatric
    0.46
    POSITIVE LOGITS
     tecn
    0.51
     pendant
    0.40
    常用
    0.39
     tadi
    0.39
    棻
    0.39
    انے
    0.38
     Karya
    0.38
     technique
    0.38
     pratic
    0.38
    含量
    0.38
    Activations Density 0.022%

    No Known Activations