© 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. 5174
    Prev
    Next
    INDEX
    Explanations

    phrase

    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
     wry
    0.59
     literally
    0.54
     ½
    0.50
     GI
    0.49
     deliver
    0.48
     forment
    0.48
    €˜
    0.47
     �
    0.46
     ‘
    0.46
     --
    0.46
    POSITIVE LOGITS
    ًا
    0.65
     subpar
    0.59
     تقریباً
    0.52
     XNUMX
    0.51
     ​​
    0.49
     أيضًا
    0.49
    а
    0.47
    ᵉ
    0.47
     asimismo
    0.45
    သောအ
    0.45
    Activations Density 0.016%

    No Known Activations