© 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. 47869
    Prev
    Next
    INDEX
    Explanations

    punctuation and English 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_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
     ומ
    0.52
    
    0.50
    t
    0.49
     neoc
    0.49
     dant
    0.47
     ===
    0.46
     fever
    0.45
     (!)
    0.45
    
    0.45
    ş
    0.44
    POSITIVE LOGITS
    чный
    0.48
     najwięks
    0.44
     wpły
    0.43
    环保
    0.43
     Nachhalt
    0.42
     wyjątk
    0.42
    Forever
    0.42
    NumConst
    0.42
     Forever
    0.41
     indywidual
    0.41
    Activations Density 0.031%

    No Known Activations